© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    the

    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
     autorytatywna
    -0.70
    +#+#
    -0.69
    enumii
    -0.65
    RenderAtEndOf
    -0.60
    Autoritní
    -0.59
    ,‎
    -0.55
    Хьажоргаш
    -0.54
    errHandler
    -0.54
    ็จ
    -0.54
    حياته
    -0.53
    POSITIVE LOGITS
     virus
    0.54
     contagious
    0.53
    eci
    0.53
     a
    0.52
     Initialized
    0.50
    badlogic
    0.50
     potentially
    0.49
     institutional
    0.48
     lateinit
    0.47
     dangerous
    0.47
    Activations Density 0.000%

    No Known Activations