© 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. 20-CLT-HP
    7. 77522
    Prev
    Next
    INDEX
    Explanations

    Technical project names/snippets

    np_max-act-logits · 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
     kasarigan
    -0.61
    mbic
    -0.61
    createCanvas
    -0.59
    Życiorys
    -0.58
    withIdentifier
    -0.58
    iela
    -0.56
    ingles
    -0.55
    BeginContext
    -0.54
    rungsseite
    -0.54
    GraphicsUnit
    -0.54
    POSITIVE LOGITS
    DockStyle
    0.54
    AnimationsModule
    0.53
    zkiem
    0.47
    thenReturn
    0.43
    öscht
    0.43
    AddTagHelper
    0.41
     captures
    0.41
     capturing
    0.41
    erts
    0.41
     recover
    0.40
    Activations Density 0.000%

    No Known Activations