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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11196
    Prev
    Next
    INDEX
    Explanations

    perspective

    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
     perspective
    -0.90
     Perspective
    -0.87
    perspective
    -0.84
    Perspective
    -0.77
     perspectiva
    -0.73
     perspectives
    -0.73
     prospet
    -0.71
     PERSPECT
    -0.67
     perspec
    -0.57
     perspek
    -0.56
    POSITIVE LOGITS
    ConstraintMaker
    0.63
    createStatement
    0.57
    abend
    0.54
    ثيق
    0.54
     star
    0.54
     muualla
    0.54
    proba
    0.54
     save
    0.53
    ParallelGroup
    0.52
    ]%
    0.52
    Activations Density 0.034%

    No Known Activations