© 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. 91806
    Prev
    Next
    INDEX
    Explanations

    reproduction

    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
    ViewChild
    -0.45
     فريبيس
    -0.45
    tainty
    -0.42
    illips
    -0.42
    genommen
    -0.41
    DebuggerNonUser
    -0.41
    tometer
    -0.40
    出版年
    -0.40
    othesis
    -0.39
    titut
    -0.39
    POSITIVE LOGITS
    SharedCtor
    0.96
    intios
    0.72
    __*/
    0.66
    MLLoader
    0.63
     Numerade
    0.62
    elemField
    0.60
    homonymie
    0.60
     Silla
    0.58
     Riproduzione
    0.58
    setVerticalGroup
    0.57
    Activations Density 0.001%

    No Known Activations