© 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. 12-RES-MATRYOSHKA-DC
    7. 30220
    Prev
    Next
    INDEX
    Explanations

    evidence or references to scientific studies and their findings

    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
     nahilalakip
    -0.65
     Pary
    -0.57
     materna
    -0.56
     lethal
    -0.54
    MethodManager
    -0.54
     [@
    -0.54
     Jocelyn
    -0.53
    ForResult
    -0.52
     Tetrahedron
    -0.52
     tphcm
    -0.52
    POSITIVE LOGITS
     StatelessWidget
    0.84
     незавершена
    0.78
    findpost
    0.70
     ""],
    0.69
    migrationBuilder
    0.65
    "}},
    0.60
    ngdoc
    0.60
    "])){
    0.59
    localctx
    0.58
    #+#
    0.56
    Activations Density 0.108%

    No Known Activations