© 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. 1-CLT-HP
    7. 14795
    Prev
    Next
    INDEX
    Explanations

    Different ways of doing something

    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
    different
    -0.49
     difference
    -0.48
     different
    -0.47
    Different
    -0.46
     diferente
    -0.42
     a
    -0.41
    一个
    -0.40
    differential
    -0.40
     na
    -0.39
     خارجية
    -0.39
    POSITIVE LOGITS
     myſelf
    0.87
     חיצוניים
    0.87
     faſt
    0.83
     Majefty
    0.82
     raiſ
    0.79
     auffi
    0.77
     ſind
    0.77
     continúas
    0.77
    ſelf
    0.76
     BoxFit
    0.76
    Activations Density 0.082%

    No Known Activations