© 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. 9882
    Prev
    Next
    INDEX
    Explanations

    difficult situations

    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
     "
    -0.46
     aus
    -0.44
    dor
    -0.41
    heit
    -0.38
    sta
    -0.38
     No
    -0.38
    ed
    -0.38
     [
    -0.38
     St
    -0.38
     (
    -0.37
    POSITIVE LOGITS
     Efq
    1.10
     myſelf
    1.02
    URLException
    0.99
     Jefus
    0.95
     ſmall
    0.94
     houſe
    0.93
     pleaſure
    0.93
     ſeveral
    0.92
     whoſe
    0.91
     himſelf
    0.90
    Activations Density 0.028%

    No Known Activations