© 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. 0-CLT-HP
    4. 91205
    Prev
    Next
    INDEX
    Explanations

    value/usefulness

    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
    useful
    -1.02
     useful
    -0.96
    Useful
    -0.91
     Useful
    -0.88
     valioso
    -0.75
    CppMethod
    -0.74
    universal
    -0.74
     valuable
    -0.73
    ⓧ
    -0.73
    rrggbb
    -0.70
    POSITIVE LOGITS
    ly
    0.63
    createObject
    0.52
     occasion
    0.51
     order
    0.51
     adulthood
    0.51
     element
    0.49
     image
    0.49
     goods
    0.49
     fic
    0.49
     apparel
    0.49
    Activations Density 0.053%

    No Known Activations