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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92415
    Prev
    Next
    INDEX
    Explanations

    normality

    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
     Roskov
    -0.94
     Efq
    -0.84
     adulthood
    -0.82
     normality
    -0.79
     Paglinawan
    -0.74
     Theſe
    -0.74
    copg
    -0.70
    LElement
    -0.69
     normalcy
    -0.69
    stdc
    -0.69
    POSITIVE LOGITS
    是以
    0.50
    Buongiorno
    0.47
     is
    0.47
    uoco
    0.47
    verifyException
    0.45
    a
    0.44
    %%%%%%%%%%%%%%%%
    0.43
    pum
    0.43
    Vendo
    0.43
     Was
    0.42
    Activations Density 0.498%

    No Known Activations