© 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. 17821
    Prev
    Next
    INDEX
    Explanations

    phrases related to video rental availability and settings preferences

    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
    <eos>
    -0.58
     (
    -0.44
    Portály
    -0.42
     |
    -0.40
     geï
    -0.39
    みた
    -0.39
    ↵↵
    -0.39
    *
    -0.38
     kazan
    -0.38
     sola
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.99
    Билгалдахарш
    0.93
     Reſ
    0.87
    참고
    0.85
     Roskov
    0.83
     ſmall
    0.81
    parsedMessage
    0.81
    rawDesc
    0.79
    évaluateur
    0.78
    CrossRef
    0.77
    Activations Density 0.001%

    No Known Activations