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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2081
    Prev
    Next
    INDEX
    Explanations

    academic studies

    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
    ksesta
    -0.54
    #+#
    -0.52
     marito
    -0.50
    Hauptartikel
    -0.50
     jadx
    -0.47
     tarvit
    -0.46
     réglable
    -0.46
     poveznice
    -0.45
    êcher
    -0.43
    szön
    -0.43
    POSITIVE LOGITS
     estekak
    0.76
    QMetaType
    0.65
     ویکی‌پدیا
    0.62
    SharedCtor
    0.60
    קישורים
    0.59
    Referencies
    0.55
    ceutical
    0.54
    PING
    0.52
    Odkazy
    0.51
    Brainz
    0.50
    Activations Density 0.000%

    No Known Activations