© 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. 44149
    Prev
    Next
    INDEX
    Explanations

    sizes

    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
     Efq
    -0.88
     outliers
    -0.82
     élevées
    -0.78
     poffible
    -0.77
     ainfi
    -0.75
     itſelf
    -0.75
    XL
    -0.74
     raiſ
    -0.73
     Majefty
    -0.73
     engraçadas
    -0.71
    POSITIVE LOGITS
    AddTagHelper
    0.62
    balleur
    0.51
    TRAILING
    0.50
     continued
    0.50
    jooq
    0.49
    sana
    0.48
    ⁩
    0.48
    ians
    0.47
    ArrowToggle
    0.47
    ematic
    0.47
    Activations Density 1.608%

    No Known Activations