© 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. 1-CLT-HP
    7. 13768
    Prev
    Next
    INDEX
    Explanations

    academic

    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
    OuterClass
    -0.47
     {
    -0.42
    спита
    -0.41
    ธ
    -0.41
     Traum
    -0.41
     ery
    -0.40
     educational
    -0.40
    GeoNames
    -0.40
    amai
    -0.40
     väl
    -0.40
    POSITIVE LOGITS
    ConstraintMaker
    0.98
     Orrell
    0.66
    ngths
    0.64
     itſelf
    0.63
    Sklici
    0.63
    Składniki
    0.63
     servos
    0.63
     mijne
    0.61
    tvguidetime
    0.61
     Jefus
    0.61
    Activations Density 0.005%

    No Known Activations