© 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. 45093
    Prev
    Next
    INDEX
    Explanations

    location description

    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
    -1.38
     pleaſure
    -1.33
     itſelf
    -1.28
     purpoſe
    -1.21
     Jefus
    -1.20
     Majefty
    -1.20
     photolibrary
    -1.17
     Мексичка
    -1.16
     uſe
    -1.14
     ſtate
    -1.12
    POSITIVE LOGITS
     
    1.05
     A
    0.85
     (
    0.84
     at
    0.83
     The
    0.77
     L
    0.77
     in
    0.75
     K
    0.75
     M
    0.74
     I
    0.73
    Activations Density 0.083%

    No Known Activations