© 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. 90923
    Prev
    Next
    INDEX
    Explanations

    attitude

    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
     trust
    -1.47
     Trust
    -1.25
    trust
    -1.23
     TRUST
    -1.11
    Trust
    -1.09
     trusts
    -1.03
     trusting
    -0.98
     style
    -0.94
    style
    -0.94
     styles
    -0.94
    POSITIVE LOGITS
     OSError
    0.54
    ficulties
    0.52
    ButtonModule
    0.51
    MotionEvent
    0.47
    WAUKEE
    0.47
     experimentally
    0.46
     Exchequer
    0.45
     Ngb
    0.43
     promp
    0.43
    RoutingModule
    0.43
    Activations Density 0.250%

    No Known Activations