© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12641
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or prohibition

    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
    1253
    +0.12
    0.3%
    872
    +0.08
    0.2%
    441
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.12
    0.05
    1285
    +0.08
    0.05
    1695
    +0.08
    0.04
    Negative Logits
     frau
    -0.95
     kram
    -0.93
     errone
    -0.93
     Kategor
    -0.92
     reger
    -0.92
     makro
    -0.91
     Nö
    -0.89
     elek
    -0.85
     profi
    -0.85
     hek
    -0.84
    POSITIVE LOGITS
    <bos>
    1.01
     nor
    0.69
     مرئيه
    0.66
    Rozm
    0.63
     anymore
    0.62
     pojaw
    0.58
     anything
    0.57
     or
    0.56
    Witaj
    0.53
    Rozmiar
    0.52
    Activations Density 0.355%

    No Known Activations