© 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. 0-CLT-HP
    7. 93889
    Prev
    Next
    INDEX
    Explanations

    m

    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
     
    -1.92
     (
    -1.67
     I
    -1.62
     d
    -1.59
     a
    -1.58
     t
    -1.56
     c
    -1.55
     p
    -1.54
     in
    -1.54
     m
    -1.52
    POSITIVE LOGITS
     myſelf
    3.63
     itſelf
    3.47
     Efq
    3.36
     Anſ
    3.28
    ſelf
    3.27
     Majefty
    3.27
     pleaſure
    3.27
     purpoſe
    3.25
     Jefus
    3.20
     Monfieur
    3.19
    Activations Density 0.387%

    No Known Activations