© 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. 0-CLT-HP
    7. 94682
    Prev
    Next
    INDEX
    Explanations

    encryption and data manipulation

    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
    providedIn
    -0.87
    posedge
    -0.79
    DockStyle
    -0.76
     BrowserModule
    -0.71
     Roskov
    -0.71
    TagMode
    -0.70
     الحره
    -0.70
    pexpr
    -0.69
     HomeController
    -0.69
    Mains
    -0.68
    POSITIVE LOGITS
    ings
    0.81
    off
    0.64
    outs
    0.64
    -
    0.63
    out
    0.60
    ers
    0.56
    set
    0.53
    ness
    0.53
    cast
    0.52
    load
    0.52
    Activations Density 0.058%

    No Known Activations