© 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. 4-CLT-HP
    7. 4358
    Prev
    Next
    INDEX
    Explanations

    modifications

    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
    شهاد
    -0.68
     صوتيه
    -0.57
    PullParser
    -0.57
    Especificaciones
    -0.57
    ittles
    -0.55
    NavController
    -0.54
    tears
    -0.53
    routeProvider
    -0.52
    openhauer
    -0.52
    ständen
    -0.52
    POSITIVE LOGITS
     Properly
    0.86
     properly
    0.83
     correctly
    0.77
     correctamente
    0.68
     appropriately
    0.67
    properly
    0.61
     adecuadamente
    0.58
     incorrectly
    0.57
     corretamente
    0.56
    Clearly
    0.55
    Activations Density 0.004%

    No Known Activations