© 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. 403
    Prev
    Next
    INDEX
    Explanations

    ultrasound

    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
     particulières
    -0.57
    modelBuilder
    -0.50
     enfans
    -0.50
     méri
    -0.49
     complètes
    -0.49
     normaux
    -0.48
     "..\..\..\
    -0.48
    IBAction
    -0.48
     "..\..\
    -0.47
     JpaRepository
    -0.47
    POSITIVE LOGITS
    (!__
    0.60
    sidemargin
    0.59
     transfieras
    0.55
    ranton
    0.54
    LookAnd
    0.53
    HomeAsUpEnabled
    0.53
     Jon
    0.53
     disambiguazione
    0.52
    ismet
    0.51
    Ход
    0.50
    Activations Density 0.006%

    No Known Activations