© 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. 12-RES-MATRYOSHKA-DC
    7. 23084
    Prev
    Next
    INDEX
    Explanations

    specific data points and numerical values in the context of statistics and measurements

    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
     rire
    -0.45
    Aceptar
    -0.45
    Distribuzione
    -0.44
     összes
    -0.43
     on
    -0.42
    pēc
    -0.41
     Verordnung
    -0.41
     in
    -0.41
    不等
    -0.40
     šte
    -0.40
    POSITIVE LOGITS
     незавершена
    0.96
     saites
    0.92
     للمعارف
    0.85
     المعيارى
    0.78
     BoxDecoration
    0.77
     שוליים
    0.73
     Waray
    0.73
    tvguidetime
    0.72
    ostante
    0.71
    UnknownFieldSet
    0.69
    Activations Density 0.029%

    No Known Activations