© 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. 20-CLT-HP
    7. 73113
    Prev
    Next
    INDEX
    Explanations

    Time periods or funding

    np_max-act-logits · 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
     Abp
    -0.74
    IsContent
    -0.73
    цездатний
    -0.69
    äldrar
    -0.66
    ɵɵ
    -0.64
    matchCondition
    -0.62
     Sider
    -0.62
    )";
    -0.62
    DECREF
    -0.61
    ://$
    -0.61
    POSITIVE LOGITS
     year
    0.60
     semester
    0.45
    able
    0.43
    alised
    0.38
    {
    0.37
    Diweddarwch
    0.37
    kering
    0.36
    liese
    0.36
    6
    0.36
    alisasi
    0.36
    Activations Density 0.002%

    No Known Activations