© 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. 4-CLT-HP
    7. 439
    Prev
    Next
    INDEX
    Explanations

    hair

    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
    AddTagHelper
    -0.61
     الرياضيه
    -0.51
    帛
    -0.49
    otra
    -0.48
    SerializedName
    -0.48
    olan
    -0.47
     فريبيس
    -0.46
     teatr
    -0.46
    NewLabel
    -0.45
    bcryptjs
    -0.45
    POSITIVE LOGITS
     AudioClip
    0.57
    TestBed
    0.56
    IAP
    0.55
    XDECREF
    0.55
     VIAF
    0.54
     IAP
    0.53
     grab
    0.52
    hair
    0.50
     Weltkrieg
    0.48
     NavController
    0.48
    Activations Density 0.000%

    No Known Activations