© 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. 1-CLT-HP
    7. 12440
    Prev
    Next
    INDEX
    Explanations

    diversity

    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
    +#+#
    -0.88
    LookAnd
    -0.72
     astore
    -0.68
     bezeichneter
    -0.66
    ganu
    -0.65
    endphp
    -0.63
     الحره
    -0.62
    NGL
    -0.61
     متعلقه
    -0.60
    Obrázky
    -0.60
    POSITIVE LOGITS
     of
    0.83
     seuls
    0.54
    XmlAccessorType
    0.53
     únicos
    0.52
     in
    0.52
     courriel
    0.51
     löyty
    0.49
     operativos
    0.48
     between
    0.47
     próprios
    0.47
    Activations Density 0.005%

    No Known Activations