© 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. 17758
    Prev
    Next
    INDEX
    Explanations

    symbols or notations used in scientific or technical contexts

    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
    CascadeType
    -0.68
    entiary
    -0.63
    ädie
    -0.57
    oa̍t
    -0.56
    liceerd
    -0.54
    BrowserModule
    -0.52
     autorisation
    -0.52
     Concepción
    -0.51
     opérateur
    -0.51
     intestino
    -0.50
    POSITIVE LOGITS
    ···
    1.04
     chi̍t
    0.66
    EDEFAULT
    0.65
    Архівовано
    0.62
    orz
    0.60
    렷
    0.59
     Tors
    0.59
    ɵɵ
    0.58
    ]--;
    0.58
    ⋱
    0.58
    Activations Density 0.000%

    No Known Activations