© 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. 5-CLT-HP
    7. 95144
    Prev
    Next
    INDEX
    Explanations

    a

    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
    they
    -0.54
    while
    -0.52
     they
    -0.50
    They
    -0.47
    .
    -0.47
     thì
    -0.46
    no
    -0.46
     to
    -0.45
    ()))
    -0.45
     we
    -0.44
    POSITIVE LOGITS
    webElementXpaths
    0.76
    انجليز
    0.75
     Signalez
    0.73
    StructEnd
    0.68
    InitVars
    0.67
     Infórmanos
    0.66
     мәкал
    0.66
    matchCondition
    0.66
    alaya
    0.63
     препратки
    0.62
    Activations Density 0.007%

    No Known Activations