© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 907
    Prev
    Next
    INDEX
    Explanations

    children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.69
     مشين
    -0.65
    }")]
    -0.63
    IntoConstraints
    -0.63
    )]
    -0.63
    ']);
    -0.63
    '];
    -0.60
    ()]);
    -0.60
    "].
    -0.60
    "];
    -0.59
    POSITIVE LOGITS
     chilen
    0.54
     lode
    0.52
     quorum
    0.47
     eaters
    0.46
     flea
    0.46
     Cæsar
    0.45
     quæ
    0.45
    Portály
    0.44
     fielding
    0.44
    ledem
    0.44
    Activations Density 0.003%

    No Known Activations