© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1936
    Prev
    Next
    INDEX
    Explanations

    ogenous

    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
    -0.98
    istically
    -0.97
     Efq
    -0.94
     Monfieur
    -0.93
     Reſ
    -0.92
     Diſ
    -0.88
     greateſt
    -0.88
     myſelf
    -0.88
     ―――――
    -0.87
     avoient
    -0.86
    POSITIVE LOGITS
    e
    0.60
     to
    0.52
     on
    0.50
     All
    0.49
     no
    0.48
     sou
    0.46
     nos
    0.45
     X
    0.45
     with
    0.44
     (
    0.44
    Activations Density 0.047%

    No Known Activations