© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2495
    Prev
    Next
    INDEX
    Explanations

    mentions of different climates and climate-related concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    528
    +0.08
    0.3%
    1828
    +0.07
    0.3%
    50
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.08
    0.03
    1435
    +0.07
    0.03
    1688
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.06
    <?
    -0.64
    ⓧ
    -0.64
    
    -0.64
     liberate
    -0.61
     abolish
    -0.61
    <?
    -0.59
     disobey
    -0.58
     erode
    -0.57
     expel
    -0.57
    POSITIVE LOGITS
     climate
    2.23
     Climate
    2.12
    Climate
    2.00
    climate
    1.93
     CLIMATE
    1.83
     klima
    1.51
     climates
    1.47
     Clim
    1.39
     climatic
    1.36
     Climat
    1.35
    Activations Density 0.135%

    No Known Activations