© 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. 5746
    Prev
    Next
    INDEX
    Explanations

    supernatant

    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
    Hochspringen
    -0.59
     GenerationType
    -0.59
    yelitis
    -0.54
    ReusableCell
    -0.54
    saraba
    -0.52
    enderror
    -0.52
    tagHelperRunner
    -0.51
    ']").
    -0.50
    -------
    -0.50
    )))));
    -0.48
    POSITIVE LOGITS
    ulink
    0.53
    üf
    0.52
     fluid
    0.50
    migrationBuilder
    0.50
     herum
    0.50
     containing
    0.49
    HasBeenSet
    0.49
     medium
    0.48
     directed
    0.48
     Examin
    0.48
    Activations Density 0.012%

    No Known Activations