© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93386
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    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
     Theſe
    -0.92
    i
    -0.92
     myſelf
    -0.86
    iya
    -0.78
    ed
    -0.77
     Jefus
    -0.77
     Anſ
    -0.77
    a
    -0.77
     Majefty
    -0.76
     houſe
    -0.75
    POSITIVE LOGITS
    san
    0.57
    sd
    0.55
    ste
    0.48
     Commencez
    0.47
     Ken
    0.47
     Tha
    0.46
    sen
    0.45
     Horn
    0.45
    ulet
    0.45
    sti
    0.44
    Activations Density 0.085%

    No Known Activations