© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75711
    Prev
    Next
    INDEX
    Explanations

    bolic

    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
    UnusedPrivate
    -0.58
     seg
    -0.53
    InvalidProtocol
    -0.51
    NameInMap
    -0.47
    лтемелер
    -0.45
     hObject
    -0.44
     AssemblyCompany
    -0.44
    ainen
    -0.43
    vosť
    -0.42
    CreateModel
    -0.42
    POSITIVE LOGITS
    HtmlAttribute
    0.73
    цездатний
    0.61
    apimachinery
    0.57
     fört
    0.56
    +:+
    0.56
     tänka
    0.55
     eenige
    0.54
    áctenos
    0.54
     musicales
    0.54
     españ
    0.54
    Activations Density 0.000%

    No Known Activations