© 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. 95046
    Prev
    Next
    INDEX
    Explanations

    Settlements

    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
    UnsafeEnabled
    -0.56
    makeConstraints
    -0.53
    vw
    -0.52
    webElementXpaths
    -0.52
     Lip
    -0.48
     Sciences
    -0.48
     Synagogue
    -0.47
    fjspx
    -0.47
    litis
    -0.47
    pis
    -0.46
    POSITIVE LOGITS
     morire
    0.61
    hyrchwyd
    0.60
     prossima
    0.57
    MessageOf
    0.57
     vervol
    0.56
    niająca
    0.56
     piattaforma
    0.54
     houſe
    0.54
    IsContent
    0.54
     in
    0.54
    Activations Density 0.002%

    No Known Activations