© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90734
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    cotch
    -1.77
    copyright
    -1.01
    🏻
    -0.60
    ticed
    -0.58
    énégal
    -0.56
    ToAction
    -0.51
    aneamente
    -0.51
     getItemId
    -0.51
    ządz
    -0.50
    swell
    -0.49
    POSITIVE LOGITS
     AttributeSet
    0.69
    Біографія
    0.60
    IUrlHelper
    0.60
    featureID
    0.59
    IntoConstraints
    0.59
     linkovi
    0.59
     OFDb
    0.57
     препратки
    0.54
     Celui
    0.53
    évaluateur
    0.52
    Activations Density 0.164%

    No Known Activations