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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7576
    Prev
    Next
    INDEX
    Explanations

    phrases related to climate change and environmental impact

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    381
    +0.14
    0.5%
    1068
    +0.14
    0.5%
    555
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1068
    +0.14
    0.08
    555
    +0.14
    0.06
    1677
    +0.14
    0.05
    Negative Logits
     sappi
    -1.33
     aen
    -1.26
     fta
    -1.23
     paff
    -1.22
     ?...
    -1.21
     seiz
    -1.20
     effe
    -1.18
     ftu
    -1.17
     stockholm
    -1.16
     aton
    -1.16
    POSITIVE LOGITS
     But
    0.73
     what
    0.68
     why
    0.67
     whether
    0.64
    But
    0.63
     yet
    0.62
     because
    0.61
     how
    0.61
     there
    0.60
    Manbalar
    0.60
    Activations Density 0.123%

    No Known Activations