© 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. 4845
    Prev
    Next
    INDEX
    Explanations

    fantasy fiction

    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
    onViewCreated
    -0.53
    abestanden
    -0.52
    SourceChecksum
    -0.46
    plato
    -0.43
     الرياضيه
    -0.42
     ویکی‌پدی
    -0.41
     natural
    -0.40
    ranton
    -0.40
     op
    -0.39
     assessment
    -0.38
    POSITIVE LOGITS
     raiſ
    0.60
    grine
    0.59
     scattata
    0.59
    batterie
    0.59
    vernight
    0.59
     uſed
    0.57
    uron
    0.56
     corrom
    0.56
    وذ
    0.56
    uronic
    0.55
    Activations Density 0.001%

    No Known Activations