© 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. 72546
    Prev
    Next
    INDEX
    Explanations

    a

    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
    verwijspagina
    -0.59
     renforcé
    -0.56
    DockStyle
    -0.56
     découver
    -0.54
     gatto
    -0.52
    PhysRev
    -0.51
     CreateTagHelper
    -0.51
     tarts
    -0.49
     luogo
    -0.49
     transfieras
    -0.49
    POSITIVE LOGITS
     estekak
    0.68
     color
    0.56
    ighted
    0.55
     vo
    0.53
    ternut
    0.50
    ENIA
    0.50
    //
    0.49
    rinfo
    0.49
    mmate
    0.49
    ArgsConstructor
    0.49
    Activations Density 0.001%

    No Known Activations