© 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. 4-CLT-HP
    7. 360
    Prev
    Next
    INDEX
    Explanations

    Code involving system input

    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
    bootstrapcdn
    -0.69
    contentLoaded
    -0.60
     Exactos
    -0.57
    RunWith
    -0.53
    PageContext
    -0.50
    $};
    -0.50
     resourceCulture
    -0.48
    uete
    -0.48
    );"
    -0.48
     rękaw
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.67
    帖最后由
    0.58
     Fontaine
    0.56
     Trouble
    0.53
    >%
    0.52
     SUDOC
    0.50
     Wishes
    0.49
    AndEndTag
    0.49
     Relationship
    0.48
    Datuak
    0.48
    Activations Density 0.026%

    No Known Activations