© 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. 1-CLT-HP
    7. 12985
    Prev
    Next
    INDEX
    Explanations

    location

    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
     iprot
    -0.66
     myſelf
    -0.64
    +#+
    -0.63
    évaluateur
    -0.62
     Walkover
    -0.61
    etcode
    -0.60
     Majefty
    -0.60
     AssemblyProduct
    -0.60
    webElementXpaths
    -0.60
     Cirque
    -0.59
    POSITIVE LOGITS
    bo
    0.56
    rawDesc
    0.53
    be
    0.52
    .
    0.47
    Referències
    0.47
     FISCAL
    0.46
     of
    0.45
    -
    0.45
    he
    0.45
    principalTable
    0.45
    Activations Density 0.313%

    No Known Activations