© 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. 1-CLT-HP
    7. 9903
    Prev
    Next
    INDEX
    Explanations

    dominant

    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
     Majefty
    -0.80
     photolibrary
    -0.79
     Jefus
    -0.78
     voodoo
    -0.77
    :+:
    -0.77
    TypedDataSet
    -0.77
     Efq
    -0.77
     Moslem
    -0.76
    évaluateur
    -0.75
     Chrift
    -0.75
    POSITIVE LOGITS
    '
    0.52
     position
    0.46
     e
    0.45
     pos
    0.45
    ’
    0.44
    position
    0.44
     C
    0.43
     U
    0.43
     player
    0.43
    ing
    0.43
    Activations Density 0.006%

    No Known Activations