© 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. 25058
    Prev
    Next
    INDEX
    Explanations

    instances of the word "case" in varying formats and numbers

    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
    Negative Logits
     NUKAT
    -0.68
    Ecotoxicity
    -0.68
     Meksiku
    -0.67
    ]--;
    -0.66
    )();
    -0.63
    SPECTION
    -0.60
     ()
    -0.60
    Tikang
    -0.60
     Gauthier
    -0.60
    ()}}
    -0.60
    POSITIVE LOGITS
     كومونز
    0.63
    ModelState
    0.59
    featureID
    0.59
     CASE
    0.58
    ContentAlignment
    0.58
    échelle
    0.57
    CASE
    0.57
    RectangleBorder
    0.57
    Dade
    0.56
    DOCTYPE
    0.55
    Activations Density 0.015%

    No Known Activations