© 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. 44204
    Prev
    Next
    INDEX
    Explanations

    write

    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
     myſelf
    -1.16
     Efq
    -1.13
     Wrote
    -1.05
    ſelves
    -1.04
     Jefus
    -1.02
     purpoſe
    -1.01
    ########.
    -1.00
     ſeveral
    -0.96
     themſelves
    -0.96
     reaſon
    -0.96
    POSITIVE LOGITS
    /
    0.69
     the
    0.68
     (
    0.64
     
    0.63
     V
    0.60
     “
    0.60
     /
    0.59
    :
    0.59
    a
    0.58
    (
    0.58
    Activations Density 0.245%

    No Known Activations