© 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. 5-CLT-HP
    7. 5293
    Prev
    Next
    INDEX
    Explanations

    total

    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
     pinulongan
    -0.82
    GEBURTSDATUM
    -0.75
    MigrationBuilder
    -0.73
    styleType
    -0.72
    Tikang
    -0.70
    ViewFeatures
    -0.66
    __((
    -0.63
    Portale
    -0.60
     intptr
    -0.59
    StoryboardSegue
    -0.58
    POSITIVE LOGITS
     sample
    0.62
     n
    0.60
    requireNonNull
    0.54
     N
    0.52
    తా
    0.52
    yargs
    0.52
     vald
    0.50
    ΙΚ
    0.49
    unhofer
    0.48
     of
    0.48
    Activations Density 0.015%

    No Known Activations