© 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. 12148
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    Ok
    -0.62
    OK
    -0.56
    —
    -0.55
    Bonsoir
    -0.55
    Okay
    -0.54
     OK
    -0.53
    :
    -0.51
     correspon
    -0.49
    째
    -0.48
     JUGA
    -0.48
    POSITIVE LOGITS
     themſelves
    0.75
     myſelf
    0.75
     itſelf
    0.73
    ſelf
    0.73
    neſs
    0.73
    GEBURTSDATUM
    0.72
    ſelves
    0.71
     ſeveral
    0.69
    SourceChecksum
    0.68
     ſtate
    0.67
    Activations Density 0.026%

    No Known Activations