© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12282
    Prev
    Next
    INDEX
    Explanations

    :

    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
    (!__
    -0.94
     defaultstate
    -0.93
    OGND
    -0.91
     betweenstory
    -0.90
    AddTagHelper
    -0.89
    цездатний
    -0.87
    Rüyada
    -0.87
     للاسماء
    -0.86
     pinulongan
    -0.84
     intptr
    -0.83
    POSITIVE LOGITS
    fic
    0.52
    kjø
    0.48
    ACES
    0.48
    asure
    0.47
    nesse
    0.47
    ality
    0.46
    mesa
    0.46
    āv
    0.46
    hood
    0.46
    vén
    0.46
    Activations Density 0.010%

    No Known Activations