© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91112
    Prev
    Next
    INDEX
    Explanations

    giorno

    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
     
    -0.84
     F
    -0.76
     B
    -0.73
     K
    -0.73
    W
    -0.72
     P
    -0.70
     W
    -0.70
     I
    -0.70
    K
    -0.69
     A
    -0.68
    POSITIVE LOGITS
     myſelf
    2.50
     itſelf
    2.31
     Efq
    2.19
    ſelves
    2.16
     Jefus
    2.16
     purpoſe
    2.14
     Majefty
    2.14
    ſelf
    2.11
     themſelves
    2.11
     raiſ
    2.11
    Activations Density 0.309%

    No Known Activations