© 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. 0-CLT-HP
    7. 41203
    Prev
    Next
    INDEX
    Explanations

    bili

    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
    IUrlHelper
    -0.77
    aarrggbb
    -0.70
    évaluateur
    -0.67
     ModelExpression
    -0.66
    enumi
    -0.65
     CreateTagHelper
    -0.64
     correctes
    -0.63
    mphony
    -0.62
    rungsseite
    -0.61
    锈钢
    -0.60
    POSITIVE LOGITS
     iconFacebook
    0.53
    dificio
    0.50
    myspace
    0.50
    bjerg
    0.49
    $.}
    0.46
    setAccessible
    0.45
    $_['
    0.44
    Auszeichnungen
    0.44
    zner
    0.44
    eurovision
    0.43
    Activations Density 0.031%

    No Known Activations