© 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. 92468
    Prev
    Next
    INDEX
    Explanations

    gas

    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
     Signalez
    -0.81
    Gambas
    -0.75
    ///</
    -0.74
     &___
    -0.69
    Geplaatst
    -0.67
     виправивши
    -0.67
    MigrationBuilder
    -0.60
    rungsseite
    -0.58
    principalTable
    -0.57
    DeleteBehavior
    -0.57
    POSITIVE LOGITS
     reserve
    0.61
     reserves
    0.52
    stones
    0.48
    reserve
    0.47
     Reserves
    0.46
    endwhile
    0.45
    Ps
    0.45
    tuck
    0.44
    TryParse
    0.44
    tigs
    0.43
    Activations Density 0.001%

    No Known Activations