© 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. 415
    Prev
    Next
    INDEX
    Explanations

    and

    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
     (
    -0.75
    —
    -0.72
     –
    -0.69
     we
    -0.68
     I
    -0.68
    …
    -0.59
     so
    -0.58
    ‑
    -0.57
    –
    -0.57
     (‘
    -0.56
    POSITIVE LOGITS
     purpoſe
    0.81
     pleaſure
    0.81
     themſelves
    0.80
     Majefty
    0.79
     ſtate
    0.75
     ainfi
    0.75
     auffi
    0.75
    expandindo
    0.75
     fhew
    0.75
     reaſon
    0.73
    Activations Density 0.006%

    No Known Activations