© 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. 91569
    Prev
    Next
    INDEX
    Explanations

    snail

    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
     defaultstate
    -0.74
     AssemblyCulture
    -0.64
     Meksiku
    -0.59
     linkovi
    -0.54
    CompleteListener
    -0.48
    expandindo
    -0.48
    FailureListener
    -0.48
     esternos
    -0.47
    PerformLayout
    -0.47
    tagHelperRunner
    -0.46
    POSITIVE LOGITS
     kautta
    0.57
     mukana
    0.54
    ivably
    0.54
    ubwa
    0.53
     positivas
    0.52
     Modern
    0.51
    !("{
    0.51
     mög
    0.50
    ruik
    0.49
     Endocrinology
    0.49
    Activations Density 0.156%

    No Known Activations