© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45404
    Prev
    Next
    INDEX
    Explanations

    titution

    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
     club
    -0.79
    ima
    -0.68
    mentation
    -0.65
    imah
    -0.64
     clubs
    -0.63
    club
    -0.52
    AsUp
    -0.52
    Ifc
    -0.52
     klub
    -0.48
    clubs
    -0.48
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.71
    tagHelperRunner
    0.61
    Datuak
    0.61
    ViewImports
    0.61
     Audiodateien
    0.59
    Filmografie
    0.59
    InjectAttribute
    0.56
    nodoc
    0.56
    abestanden
    0.54
    reicht
    0.54
    Activations Density 0.879%

    No Known Activations