© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6033
    Prev
    Next
    INDEX
    Explanations

    constant

    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
    tagHelper
    -0.59
    cinogenicity
    -0.56
    ngOnInit
    -0.54
    providedIn
    -0.52
    salm
    -0.52
    farin
    -0.52
    mijn
    -0.52
    sprecher
    -0.50
    ==",
    -0.49
     billeder
    -0.49
    POSITIVE LOGITS
     movement
    0.73
     motion
    0.71
     movimiento
    0.65
     change
    0.63
     Movement
    0.58
     movimento
    0.57
    movimiento
    0.57
     MOVEMENT
    0.56
     resourceCulture
    0.56
    motion
    0.55
    Activations Density 0.003%

    No Known Activations