© 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. 2429
    Prev
    Next
    INDEX
    Explanations

    dollar symbols followed by a number

    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
    migrationBuilder
    -0.84
    SourceChecksum
    -0.75
    jooq
    -0.65
     JADX
    -0.62
    $}}
    -0.61
    HasAnnotation
    -0.59
    expandindo
    -0.58
    interopRequire
    -0.56
    PreInfinity
    -0.56
    })}$
    -0.56
    POSITIVE LOGITS
    енча
    0.54
    ArgsConstructor
    0.50
     Donahue
    0.48
    _{\
    0.45
    ________,
    0.45
    বি
    0.44
    URLException
    0.44
    dshaw
    0.44
    ijão
    0.44
     salpic
    0.43
    Activations Density 0.050%

    No Known Activations