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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5158
    Prev
    Next
    INDEX
    Explanations

    Polls and reports

    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
     resourceCulture
    -0.73
    $_['
    -0.62
     oprot
    -0.56
     calendriers
    -0.53
     penger
    -0.52
    GetAxis
    -0.50
     出版
    -0.50
     Autres
    -0.50
    ]';
    -0.49
     EconPapers
    -0.48
    POSITIVE LOGITS
     Hillary
    0.59
     Conservatives
    0.50
     conservatives
    0.50
     Bernie
    0.49
     Duterte
    0.48
     Sush
    0.48
    ngdoc
    0.48
     puissiez
    0.47
     decreasing
    0.47
     Haaland
    0.47
    Activations Density 0.005%

    No Known Activations