© 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. 1076
    Prev
    Next
    INDEX
    Explanations

    career and education

    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
     CreateTagHelper
    -1.10
    +#+#
    -0.82
    IntoConstraints
    -0.74
     חיצוניים
    -0.72
     '\\;'
    -0.71
    WriteBarrier
    -0.70
    ReusableCell
    -0.69
     BoxFit
    -0.68
     ligiloj
    -0.68
     مشين
    -0.67
    POSITIVE LOGITS
     meta
    0.45
     typically
    0.38
     strong
    0.38
     effective
    0.35
    tulo
    0.35
     Faro
    0.34
     halo
    0.34
     nothing
    0.34
    melidir
    0.34
    meta
    0.33
    Activations Density 0.001%

    No Known Activations