© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2138
    Prev
    Next
    INDEX
    Explanations

    case

    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
    MigrationBuilder
    -0.71
    HasIndex
    -0.66
     Dafür
    -0.57
    ]--;
    -0.52
     BIBSYS
    -0.52
    VIAF
    -0.51
    Билгалдахарш
    -0.51
     الاطلاع
    -0.50
    clusão
    -0.49
    Kraj
    -0.49
    POSITIVE LOGITS
     of
    0.79
     here
    0.53
     BoxFit
    0.52
     anymore
    0.52
     EventArgs
    0.50
     with
    0.49
    richTextPanel
    0.47
    newtheorem
    0.45
    Démographie
    0.45
    lof
    0.45
    Activations Density 0.001%

    No Known Activations