© 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. 1-CLT-HP
    7. 15663
    Prev
    Next
    INDEX
    Explanations

    localized

    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
    hoeddwyd
    -0.71
    ArrowToggle
    -0.60
    RTCF
    -0.59
    withstanding
    -0.58
     متعلقه
    -0.56
    fool
    -0.56
    出版年
    -0.53
     local
    -0.53
    ]]:
    -0.53
    OfType
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.66
     Dostupné
    0.54
     pinulongan
    0.54
    ToBounds
    0.48
     Insee
    0.46
    PreExecute
    0.46
    TableHead
    0.46
    ActiveRecord
    0.45
     Normdatei
    0.45
    Portale
    0.45
    Activations Density 0.024%

    No Known Activations