© 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. 95286
    Prev
    Next
    INDEX
    Explanations

    measurements or quantities

    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
    enterOuterAlt
    -0.85
    AppMethodBeat
    -0.63
    MethodManager
    -0.63
    OGND
    -0.62
     оригіналу
    -0.60
     TextInputType
    -0.56
    ditto
    -0.55
    Datuak
    -0.53
    日閲覧
    -0.52
    Portály
    -0.52
    POSITIVE LOGITS
    adaptiveStyles
    0.60
     Majefty
    0.58
     noft
    0.57
    acad
    0.54
     décontract
    0.54
    ſelf
    0.52
     Efq
    0.52
     gratuitement
    0.51
     houſe
    0.51
     nghi
    0.51
    Activations Density 0.055%

    No Known Activations