© 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. 42943
    Prev
    Next
    INDEX
    Explanations

    finance/government related text

    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
     rayures
    -0.74
    tahankan
    -0.69
     étoient
    -0.66
     vostri
    -0.66
    STRUCTIONS
    -0.65
     acque
    -0.65
     tasche
    -0.63
     acciaio
    -0.62
     policiales
    -0.62
     egne
    -0.62
    POSITIVE LOGITS
    DockStyle
    0.77
    featureID
    0.77
    KommentareTeilen
    0.73
    MigrationBuilder
    0.72
    ValueStyle
    0.66
    ThemeOverlay
    0.64
    IUrlHelper
    0.62
    +#+#
    0.59
    achal
    0.56
    aarrggbb
    0.55
    Activations Density 0.077%

    No Known Activations