© 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. 0-CLT-HP
    7. 41862
    Prev
    Next
    INDEX
    Explanations

    technical data/identifiers

    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
    ThroughAttribute
    -0.75
    Demografía
    -0.69
     ***!
    -0.65
    #+#
    -0.57
    Tembelea
    -0.56
    nalités
    -0.53
    localctx
    -0.51
    hoga
    -0.50
     politiker
    -0.50
    الصفحه
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.89
    ]--;
    0.66
    tagHelperRunner
    0.59
    ();
    0.57
    ]='\
    0.56
    ]!='
    0.54
    migrationBuilder
    0.54
     ioutil
    0.53
     joaat
    0.52
    PhysRevD
    0.51
    Activations Density 0.696%

    No Known Activations