© 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. 93882
    Prev
    Next
    INDEX
    Explanations

    unct

    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
     MainAxisSize
    -0.72
    unct
    -0.70
     الحره
    -0.68
    LookAnd
    -0.68
     NSCoder
    -0.68
     Linking
    -0.67
     bezeichneter
    -0.67
     TextInputType
    -0.67
     rush
    -0.67
     revive
    -0.65
    POSITIVE LOGITS
    brainly
    0.43
     plages
    0.43
    Beruf
    0.43
     culturali
    0.41
    ers
    0.41
     disponibilités
    0.40
    Obrázky
    0.40
    uvo
    0.39
    драт
    0.39
    rália
    0.39
    Activations Density 0.210%

    No Known Activations