© 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. 5-CLT-HP
    7. 94069
    Prev
    Next
    INDEX
    Explanations

    code, technical documents

    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
    MarshalTo
    -0.52
     <=",
    -0.50
    LookAnd
    -0.48
    IsContent
    -0.45
    InSection
    -0.44
     Préférences
    -0.44
    liothèque
    -0.43
     jLabel
    -0.43
    ьаж
    -0.42
    ArgsConstructor
    -0.41
    POSITIVE LOGITS
    PositiveButton
    0.68
    Искәрмәләр
    0.66
     Theſe
    0.65
    RenderAtEndOf
    0.65
    iring
    0.64
    space
    0.63
    VELAND
    0.63
     charité
    0.62
    pires
    0.61
    MigrationBuilder
    0.60
    Activations Density 0.004%

    No Known Activations