© 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. 97534
    Prev
    Next
    INDEX
    Explanations

    what how

    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
     for
    -0.70
     on
    -0.68
     What
    -0.61
     in
    -0.58
     or
    -0.57
     of
    -0.55
     up
    -0.55
     from
    -0.54
     against
    -0.53
     (
    -0.52
    POSITIVE LOGITS
     ſtate
    0.99
     purpoſe
    0.91
     itſelf
    0.90
     myſelf
    0.85
     Theſe
    0.84
    __":
    0.84
     Италијани
    0.83
     theſe
    0.82
     ſtill
    0.81
     houſe
    0.81
    Activations Density 0.061%

    No Known Activations