© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1302
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of systems and inventions

    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
    NOPQRST
    -0.93
     Lightboxes
    -0.69
     <=",
    -0.66
    AnimationsModule
    -0.66
     AssemblyCulture
    -0.66
    MigrationBuilder
    -0.64
     HasFactory
    -0.62
    twimg
    -0.61
     saites
    -0.61
    (")");
    -0.60
    POSITIVE LOGITS
     trajets
    0.53
     betweenstory
    0.52
    SceneManagement
    0.51
    Portail
    0.48
    DialogResult
    0.48
     DialogResult
    0.48
    dropIfExists
    0.46
    IVEREF
    0.45
    省市镇
    0.45
    ApiModel
    0.44
    Activations Density 14.113%

    No Known Activations