© 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. 29778
    Prev
    Next
    INDEX
    Explanations

    references to classification systems and categories

    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
    رشف
    -0.81
     ivelany
    -0.79
    findpost
    -0.75
    SourceChecksum
    -0.70
    AndEndTag
    -0.67
    InjectAttribute
    -0.66
    __*/
    -0.65
    letka
    -0.65
    PreferredItem
    -0.60
    ]--;
    -0.60
    POSITIVE LOGITS
    gitte
    0.47
    теризу
    0.43
    UnitTesting
    0.42
    цездатний
    0.42
    nosaurus
    0.39
    というもの
    0.38
     közé
    0.38
    UnknownFieldSet
    0.37
     reager
    0.36
    iments
    0.35
    Activations Density 0.224%

    No Known Activations