© 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. 43578
    Prev
    Next
    INDEX
    Explanations

    formal vocabulary

    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
    IntoConstraints
    -0.82
    ConstraintMaker
    -0.77
     المعيارى
    -0.66
    aarrggbb
    -0.64
     مشين
    -0.64
    contentLoaded
    -0.62
     whither
    -0.62
    UnusedPrivate
    -0.62
    rungsseite
    -0.60
     AssemblyCulture
    -0.60
    POSITIVE LOGITS
    ,
    0.55
    TintMode
    0.53
     we
    0.50
     I
    0.49
     Donne
    0.46
    n
    0.45
    findpost
    0.45
    c
    0.44
    -
    0.42
    kind
    0.40
    Activations Density 0.013%

    No Known Activations