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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 855
    Prev
    Next
    INDEX
    Explanations

    Hawaiian dishes that include Kalua Pork

    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
    90
    +0.08
    0.2%
    1407
    +0.07
    0.2%
    1818
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.03
    283
    +0.07
    0.01
    1818
    +0.07
    0.02
    Negative Logits
     seksi
    -0.65
     Mérida
    -0.63
     Lázaro
    -0.61
     meni
    -0.61
     Mónica
    -0.61
     Áng
    -0.60
     Valentín
    -0.60
     madu
    -0.59
     pank
    -0.59
     osal
    -0.59
    POSITIVE LOGITS
    ua
    2.86
    UA
    2.00
    úa
    1.25
    uas
    1.25
     UA
    1.23
     ua
    1.22
    uan
    1.19
     parteci
    1.07
    uaa
    1.01
     sappi
    1.00
    Activations Density 0.216%

    No Known Activations