© 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. 95007
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    Viited
    -0.63
    原始内容存档于
    -0.52
    (!__
    -0.51
    НИК
    -0.50
     sockaddr
    -0.50
    __*/
    -0.49
    CompleteListener
    -0.49
    ripsi
    -0.49
    jsonwebtoken
    -0.48
    GOTREF
    -0.47
    POSITIVE LOGITS
     helping
    0.88
     giving
    0.75
     providing
    0.72
     allowing
    0.68
     TextAppearance
    0.67
    giving
    0.67
     Giving
    0.63
     aiding
    0.63
     teaching
    0.62
     Helping
    0.62
    Activations Density 0.006%

    No Known Activations