© 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. 5-CLT-HP
    7. 1938
    Prev
    Next
    INDEX
    Explanations

    requests and inquiries

    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
     jornada
    -0.40
     libres
    -0.40
    batch
    -0.40
    观
    -0.39
     posib
    -0.39
     comisión
    -0.39
    .
    -0.39
     celebrar
    -0.38
     mahdol
    -0.37
     pertinentes
    -0.36
    POSITIVE LOGITS
    parsedMessage
    1.13
    DrawerToggle
    0.94
     vPvB
    0.85
    SourceChecksum
    0.85
    OGND
    0.84
    Geplaatst
    0.80
     تضيفلها
    0.79
     IBOutlet
    0.77
    jetunion
    0.73
    zeera
    0.73
    Activations Density 0.002%

    No Known Activations