© 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. 45039
    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
    -2.13
     face
    -1.81
     Head
    -1.63
    Head
    -1.30
     Face
    -1.20
    head
    -1.10
     HEAD
    -1.06
    Face
    -0.91
     cabeza
    -0.85
     FACE
    -0.84
    POSITIVE LOGITS
     itſelf
    1.19
     myſelf
    1.19
     Monfieur
    1.13
     iſt
    1.12
     raiſ
    1.12
     ſche
    1.10
     pleaſure
    1.10
     auffi
    1.07
     Jefus
    1.06
     leſs
    1.06
    Activations Density 0.122%

    No Known Activations