© 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. 92008
    Prev
    Next
    INDEX
    Explanations

    exploited

    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
    Personendaten
    -0.83
    hie
    -0.70
    hots
    -0.67
    thâu
    -0.65
    hi
    -0.56
    NewUrlParser
    -0.55
     carros
    -0.55
     Merchandise
    -0.55
     exploited
    -0.54
     upside
    -0.53
    POSITIVE LOGITS
     BoxDecoration
    0.68
    WriteTagHelper
    0.60
     defStyle
    0.59
    ︎
    0.59
    UnusedPrivate
    0.57
     محفوظة
    0.57
     Majefty
    0.57
     onCreate
    0.56
     InputDecoration
    0.56
    ſelf
    0.54
    Activations Density 0.167%

    No Known Activations