© 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. 5-CLT-HP
    7. 97018
    Prev
    Next
    INDEX
    Explanations

    constellation

    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
     ModelExpression
    -0.96
     iprot
    -0.63
    PYX
    -0.61
    verifyException
    -0.60
     विश्वसनीयता
    -0.58
     للاسماء
    -0.56
     ujednoznacz
    -0.56
     arşivlendi
    -0.56
    tagHelperRunner
    -0.55
    requireNonNull
    -0.54
    POSITIVE LOGITS
     Où
    0.53
    纬
    0.49
     bouche
    0.48
     tradis
    0.47
    tières
    0.45
     wires
    0.45
     irré
    0.44
     lær
    0.44
    ARIUS
    0.44
    getMinutes
    0.43
    Activations Density 0.001%

    No Known Activations