© 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. 94900
    Prev
    Next
    INDEX
    Explanations

    explaining

    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
     explanation
    -1.36
    explanation
    -1.26
     explaining
    -1.25
     explanations
    -1.11
     explicación
    -0.99
     explanatory
    -0.98
     объяс
    -0.82
     AssemblyCompany
    -0.82
    Explanation
    -0.79
    lanations
    -0.77
    POSITIVE LOGITS
     متعلقه
    0.63
     Jun
    0.53
    alin
    0.51
    enci
    0.49
    בל
    0.47
    لو
    0.46
     Bartlett
    0.46
     +
    0.45
    >"+
    0.45
     Lim
    0.45
    Activations Density 0.130%

    No Known Activations