© 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. 1-CLT-HP
    7. 11893
    Prev
    Next
    INDEX
    Explanations

    site

    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
    homonymie
    -0.57
    Aktualisiert
    -0.57
     Rev
    -0.52
    listo
    -0.49
    PreferredItem
    -0.49
     disambiguazione
    -0.49
     digit
    -0.49
    gradle
    -0.49
     ModelExpression
    -0.49
    UrlResolution
    -0.47
    POSITIVE LOGITS
    Демографія
    0.67
     المعيارى
    0.67
    horabuena
    0.62
     gynhyrchwyd
    0.55
    TagMode
    0.53
     виправивши
    0.52
    Mvh
    0.51
     Meksiku
    0.50
     bēr
    0.50
    rätt
    0.49
    Activations Density 0.108%

    No Known Activations