© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15149
    Prev
    Next
    INDEX
    Explanations

    phrases related to inhibition or suppressive actions in biological contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stop
    -0.63
     stopped
    -0.63
     stop
    -0.62
     stops
    -0.58
    er
    -0.56
     STOP
    -0.56
    ם
    -0.56
     oku
    -0.55
    תק
    -0.55
     prevent
    -0.54
    POSITIVE LOGITS
    +:+
    1.04
    WriteLiteral
    1.02
    KommentareTeilen
    1.02
    RegressionTest
    0.97
    HomeAsUpEnabled
    0.94
     GenerationType
    0.92
    RetentionPolicy
    0.92
    sizeCache
    0.91
    bootstrapcdn
    0.89
     BoxDecoration
    0.89
    Activations Density 0.010%

    No Known Activations