© 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. 39953
    Prev
    Next
    INDEX
    Explanations

    woman

    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
    he
    -0.48
     this
    -0.45
     he
    -0.43
     the
    -0.42
    +#+#
    -0.42
    IntoConstraints
    -0.41
     you
    -0.40
    irk
    -0.40
    HE
    -0.39
    pay
    -0.39
    POSITIVE LOGITS
     MaterialApp
    0.91
    LookAnd
    0.73
    AsUp
    0.72
     виправивши
    0.71
     فريبيس
    0.70
    انيف
    0.68
    DrawerToggle
    0.65
     doubtnut
    0.65
    tangentMode
    0.65
     otomatig
    0.65
    Activations Density 0.177%

    No Known Activations