© 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. 18-RES-MATRYOSHKA-DC
    7. 1015
    Prev
    Next
    INDEX
    Explanations

    parts of legal documents or code segments, keying off of boilerplate language or symbols like section (§) or copyright (©).

    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.18.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.18.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
    DockStyle
    -0.66
     tartalomajánló
    -0.64
    ArgsConstructor
    -0.64
     InputDecoration
    -0.62
     HasFactory
    -0.61
     Administrativna
    -0.61
    AnchorStyles
    -0.57
    abestanden
    -0.57
     Himo
    -0.56
    出版年
    -0.55
    POSITIVE LOGITS
     Texas
    1.26
    Texas
    1.20
     Texans
    1.19
     Texan
    1.13
     TEXAS
    1.13
     texas
    1.11
     Houston
    1.11
     TX
    1.06
    texas
    1.05
     Galveston
    1.04
    Activations Density 0.576%

    No Known Activations