© 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. 5-CLT-HP
    7. 92764
    Prev
    Next
    INDEX
    Explanations

    android

    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
     imprensa
    -0.43
    ειν
    -0.43
    PILE
    -0.42
     journal
    -0.41
    omeric
    -0.40
     peines
    -0.39
    opis
    -0.39
    dataProvider
    -0.38
     invent
    -0.38
     reprint
    -0.38
    POSITIVE LOGITS
    ArgsConstructor
    0.86
    RenderAtEndOf
    0.79
     autorytatywna
    0.76
    OrNil
    0.73
    ंदीखरीदारी
    0.73
    IsContent
    0.72
     transfieras
    0.69
     @"/
    0.69
     Infórmanos
    0.69
     estekak
    0.69
    Activations Density 0.000%

    No Known Activations