© 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. 91702
    Prev
    Next
    INDEX
    Explanations

    that

    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
     <<<<<<<<<<<<<<
    -0.49
     if
    -0.49
    onedDateTime
    -0.47
     then
    -0.47
    руем
    -0.46
    ásico
    -0.45
     once
    -0.44
    luß
    -0.43
     them
    -0.41
     nếu
    -0.41
    POSITIVE LOGITS
     suits
    0.99
     you
    0.94
     Suits
    0.88
    suits
    0.82
     fits
    0.78
    TemporalType
    0.73
    you
    0.72
     suit
    0.71
     suites
    0.71
     Fits
    0.71
    Activations Density 0.005%

    No Known Activations