© 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. 94739
    Prev
    Next
    INDEX
    Explanations

    inadequ

    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
    s
    -0.82
    ness
    -0.67
     select
    -0.61
     inevitable
    -0.60
     Dur
    -0.57
    lines
    -0.54
     Goy
    -0.53
     initiative
    -0.50
    shire
    -0.49
    ship
    -0.48
    POSITIVE LOGITS
     détru
    0.72
     históricas
    0.69
     auffi
    0.68
    StoryboardSegue
    0.67
     démocr
    0.66
     myſelf
    0.66
     électriques
    0.65
     ainfi
    0.65
     StatefulWidget
    0.63
     feroit
    0.63
    Activations Density 0.212%

    No Known Activations