© 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. 5-CLT-HP
    7. 97409
    Prev
    Next
    INDEX
    Explanations

    lengthy, varied text

    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
    TagHelpers
    -0.66
    ZET
    -0.66
     Utopia
    -0.64
     Fontana
    -0.63
     Wex
    -0.63
     tedesco
    -0.62
     Bigelow
    -0.61
     Anaconda
    -0.61
     Brutus
    -0.61
     Público
    -0.61
    POSITIVE LOGITS
    цездатний
    0.54
    rungsseite
    0.52
    OGND
    0.49
     bezeichneter
    0.48
     autorytatywna
    0.48
    abestanden
    0.47
    djangoproject
    0.43
    "]));
    0.42
    "]];
    0.41
    ]));
    0.40
    Activations Density 0.570%

    No Known Activations