Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44694
    Prev
    Next
    INDEX
    Explanations

    al

    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
    hes
    -0.59
    WEBPACK
    -0.48
    lane
    -0.47
     a
    -0.47
    linux
    -0.46
     his
    -0.45
     actual
    -0.44
    name
    -0.44
    ستم
    -0.44
    los
    -0.43
    POSITIVE LOGITS
     nakalista
    0.93
    UrlResolution
    0.84
    новниш
    0.82
     disambiguazione
    0.81
     الرياضيه
    0.78
     betweenstory
    0.77
    InvalidProtocol
    0.76
     itſelf
    0.75
    tvguidetime
    0.74
     '\\;'
    0.73
    Activations Density 0.096%

    No Known Activations