© 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. 43972
    Prev
    Next
    INDEX
    Explanations

    Locations and names

    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
     Entrance
    -0.64
     Boone
    -0.61
     entrance
    -0.59
    0
    -0.56
     str
    -0.53
     Norfolk
    -0.52
    str
    -0.50
     se
    -0.50
    sek
    -0.50
    7
    -0.49
    POSITIVE LOGITS
     مرئيه
    0.95
     تانيه
    0.88
     reaſon
    0.88
     Majefty
    0.87
    ">—
    0.85
     myſelf
    0.84
     houſe
    0.84
    Хьажоргаш
    0.81
     LUMP
    0.81
     purpoſe
    0.78
    Activations Density 0.411%

    No Known Activations