© 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. 5-CLT-HP
    4. 96188
    Prev
    Next
    INDEX
    Explanations

    causes

    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
     of
    -0.68
    tof
    -0.48
     Made
    -0.46
    ards
    -0.45
     suburban
    -0.45
    ử
    -0.45
     suburbs
    -0.44
    ёв
    -0.43
     MADE
    -0.43
     Of
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.69
     championed
    0.66
     supérieures
    0.61
     démocr
    0.60
     للاسماء
    0.60
    SharedDtor
    0.60
    matchCondition
    0.60
    ArrowToggle
    0.59
     thèmes
    0.59
    onAttach
    0.59
    Activations Density 0.000%

    No Known Activations