© 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. 20-CLT-HP
    7. 77268
    Prev
    Next
    INDEX
    Explanations

    Code/Programming text

    np_max-act-logits · 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
    RectangleBorder
    -0.75
    rrggbb
    -0.69
    regado
    -0.67
     Fixed
    -0.66
     poffible
    -0.62
    팎
    -0.62
    AndEndTag
    -0.62
     Frequ
    -0.61
     quæ
    -0.61
    Pratique
    -0.61
    POSITIVE LOGITS
     NSCoder
    0.60
     '{@
    0.47
     say
    0.44
    endo
    0.43
     sorts
    0.38
    UIControl
    0.36
    рыя
    0.36
    JButton
    0.36
     sort
    0.36
     be
    0.36
    Activations Density 0.001%

    No Known Activations