© 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. 20-CLT-HP
    7. 72419
    Prev
    Next
    INDEX
    Explanations

    technical or code snippets

    np_max-act-logits · 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
    GraphicsUnit
    -0.40
    cosh
    -0.40
    YNAMIC
    -0.39
    msgTypes
    -0.39
    momix
    -0.39
     bilg
    -0.38
     få
    -0.37
    Biographie
    -0.37
    ougou
    -0.36
    MILLISECONDS
    -0.36
    POSITIVE LOGITS
     that
    1.41
    that
    0.85
     فريبيس
    0.82
     dass
    0.79
     rằng
    0.75
     bahwa
    0.68
     thats
    0.66
    }$​
    0.66
     !”
    0.65
     !"
    0.65
    Activations Density 0.000%

    No Known Activations