© 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. 5-CLT-HP
    7. 4392
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and abbreviations

    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
    KEYCODE
    -0.53
    stretchr
    -0.52
    .³
    -0.51
    estacks
    -0.48
    eabouts
    -0.47
    ofold
    -0.47
    ]]
    -0.47
    InStock
    -0.46
    umque
    -0.45
     ▪
    -0.43
    POSITIVE LOGITS
     تضيفلها
    0.59
     ProtoMessage
    0.58
     Evolution
    0.57
    ArgsConstructor
    0.56
     funniest
    0.55
     Etiquette
    0.53
     magie
    0.53
    IBOutlet
    0.53
     Achievement
    0.53
     Италијани
    0.52
    Activations Density 0.001%

    No Known Activations