© 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. 40204
    Prev
    Next
    INDEX
    Explanations

    Witch or jeopardy

    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
     witch
    -1.12
    witch
    -1.11
     Witch
    -1.05
    Witch
    -0.98
    tvguidetime
    -0.65
     jeopardy
    -0.65
    ñora
    -0.62
    raszam
    -0.57
     chré
    -0.56
    latego
    -0.54
    POSITIVE LOGITS
    ing
    0.84
    Datuak
    0.68
    ING
    0.66
    AddField
    0.62
    ed
    0.61
    esModule
    0.59
    ConstraintMaker
    0.58
    FieldOffset
    0.58
    featureID
    0.57
    ioca
    0.55
    Activations Density 1.311%

    No Known Activations