© 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. 0-CLT-HP
    7. 978
    Prev
    Next
    INDEX
    Explanations

    head

    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
     head
    -2.23
     Head
    -1.99
    Head
    -1.74
     HEAD
    -1.47
    head
    -1.37
     heads
    -1.30
    ヘッド
    -1.18
    HEAD
    -1.13
     Heads
    -1.00
     tête
    -0.93
    POSITIVE LOGITS
    CppMethod
    0.73
     snippetHide
    0.68
    yship
    0.68
     doubtnut
    0.63
     japonaise
    0.63
    psack
    0.62
    gown
    0.62
    cèse
    0.60
     Wiktionnaire
    0.60
    pozdrawiam
    0.60
    Activations Density 0.070%

    No Known Activations