© 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. 5-CLT-HP
    7. 92249
    Prev
    Next
    INDEX
    Explanations

    as

    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
    !*\
    -0.60
    帖最后由
    -0.59
    ciaż
    -0.58
     qualify
    -0.51
     getRule
    -0.47
     have
    -0.46
    especial
    -0.45
    have
    -0.45
    reveal
    -0.44
     mentioning
    -0.44
    POSITIVE LOGITS
     for
    1.50
     untuk
    0.85
     to
    0.77
    for
    0.75
     для
    0.74
     in
    0.72
     für
    0.69
    для
    0.68
     of
    0.66
     برای
    0.65
    Activations Density 0.004%

    No Known Activations