© 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. 91520
    Prev
    Next
    INDEX
    Explanations

    determine

    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
    Revenir
    -0.44
    abcdefghijklmnop
    -0.43
     personas
    -0.40
     má
    -0.39
     llamo
    -0.39
     dư
    -0.39
    odore
    -0.39
    graphers
    -0.38
    ceği
    -0.38
    sterious
    -0.38
    POSITIVE LOGITS
    EDEFAULT
    0.75
    ंदीखरीदारी
    0.69
    (!__
    0.69
     الحره
    0.68
     BoxDecoration
    0.66
     selection
    0.62
    NameInMap
    0.62
     الدولى
    0.61
    writeFieldEnd
    0.61
    InjectAttribute
    0.60
    Activations Density 0.014%

    No Known Activations