© 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. 1-CLT-HP
    7. 12222
    Prev
    Next
    INDEX
    Explanations

    postulate

    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
     postulate
    -0.98
     posit
    -0.84
     Miy
    -0.65
     appoint
    -0.58
    pow
    -0.51
     stoop
    -0.50
    ForValue
    -0.50
    pointed
    -0.50
    EMAS
    -0.49
    kommer
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.56
     Meksiku
    0.53
     estimés
    0.52
     initComponents
    0.50
    KommentareTeilen
    0.50
    brou
    0.50
     nonUne
    0.49
     تضيفلها
    0.49
    ]._
    0.47
    UserScript
    0.47
    Activations Density 0.201%

    No Known Activations