© 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. 72944
    Prev
    Next
    INDEX
    Explanations

    board

    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
    AndEndTag
    -0.84
    ArrowToggle
    -0.60
    StructEnd
    -0.59
     Signalez
    -0.57
     Normdatei
    -0.55
    AddTagHelper
    -0.53
    enumi
    -0.53
    bootstrapcdn
    -0.50
    principalTable
    -0.50
    Personensuche
    -0.50
    POSITIVE LOGITS
     архивлан
    0.50
    âmetros
    0.49
    createClass
    0.47
    featureID
    0.47
    MERCIAL
    0.47
     OkHttpClient
    0.46
    Elenco
    0.46
    لينكات
    0.46
    TimeInterval
    0.45
     Montagne
    0.45
    Activations Density 0.003%

    No Known Activations