© 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. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2704
    Prev
    Next
    INDEX
    Explanations

    words that are legal terms, amendments, and policy changes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    NOPQRST
    -0.60
    Scénario
    -0.59
    ArgsConstructor
    -0.58
    httphttps
    -0.58
     ModelExpression
    -0.57
    isholm
    -0.56
    ValueGenerated
    -0.56
     AssemblyProduct
    -0.56
     jspb
    -0.56
     eccell
    -0.54
    POSITIVE LOGITS
     effective
    1.51
    effective
    1.42
    Effective
    1.36
    EFFECT
    1.30
     Effective
    1.27
     effect
    1.23
     effectiveness
    1.18
     effec
    1.17
     EFFECTIVE
    1.15
    ffective
    1.07
    Activations Density 0.342%

    No Known Activations