© 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. 93689
    Prev
    Next
    INDEX
    Explanations

    Only option left.rese

    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
     Chris
    -0.77
     Created
    -0.62
    Chris
    -0.56
     Huge
    -0.54
     F
    -0.54
     create
    -0.53
     (
    -0.51
    Huge
    -0.50
    ed
    -0.50
     la
    -0.49
    POSITIVE LOGITS
     Efq
    1.09
     ſhe
    1.09
     purpoſe
    1.09
     ſeveral
    1.09
     Monfieur
    1.08
     itſelf
    1.05
     myſelf
    1.05
     Anſ
    1.05
     Majefty
    1.02
     ſever
    1.02
    Activations Density 0.169%

    No Known Activations