© 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. 214
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, formulas, and possibly some elements from tables

    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
    ↵↵
    -0.54
    联
    -0.46
     constitutive
    -0.45
    &
    -0.43
    "
    -0.43
    \
    -0.42
     ï
    -0.42
    <strong>
    -0.42
    </
    -0.42
    templateUrl
    -0.41
    POSITIVE LOGITS
    PerformLayout
    1.03
     disambiguazione
    0.94
    AndEndTag
    0.93
     lenker
    0.86
    Vidite
    0.85
    таратура
    0.85
    脚注の使い方
    0.84
     Administrativna
    0.84
    MigrationBuilder
    0.84
    ыгана
    0.79
    Activations Density 0.988%

    No Known Activations