© 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. 0-CLT-HP
    7. 38951
    Prev
    Next
    INDEX
    Explanations

    PAC

    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
    PAC
    -1.34
     PAC
    -1.24
    pac
    -1.23
    Pac
    -1.09
    awtextra
    -0.98
     Pac
    -0.90
    rungsseite
    -0.85
    MLLoader
    -0.82
    nemone
    -0.81
     оригіналу
    -0.81
    POSITIVE LOGITS
     Landis
    0.56
    Char
    0.53
    char
    0.48
    Anson
    0.48
    Mans
    0.46
    Man
    0.44
    Car
    0.44
     barras
    0.43
    тория
    0.43
    tabolism
    0.42
    Activations Density 0.099%

    No Known Activations