© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42958
    Prev
    Next
    INDEX
    Explanations

    phin

    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
     ph
    -0.48
     Canada
    -0.43
    ph
    -0.43
     populer
    -0.43
     potong
    -0.42
    ेटा
    -0.41
    e
    -0.40
    Canada
    -0.40
    gespräch
    -0.38
     photo
    -0.38
    POSITIVE LOGITS
     Jefus
    0.98
     purpoſe
    0.96
     itſelf
    0.94
     myſelf
    0.90
     незавершена
    0.89
     poffible
    0.87
     Diſ
    0.86
     Majefty
    0.86
     cauſe
    0.86
     HasFactory
    0.85
    Activations Density 0.050%

    No Known Activations