© 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. 4-CLT-HP
    7. 4479
    Prev
    Next
    INDEX
    Explanations

    Foundation

    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
    setVerticalGroup
    -0.90
    ReusableCell
    -0.81
    PreferredItem
    -0.72
    PerformLayout
    -0.70
    ruptcy
    -0.68
    {§
    -0.68
     NSCoder
    -0.67
    chyma
    -0.65
    SFER
    -0.65
    ,:);
    -0.65
    POSITIVE LOGITS
    lwjgl
    0.45
     indoss
    0.38
     ComVisible
    0.38
    ruptedException
    0.38
    presto
    0.37
     WELFARE
    0.37
    PREV
    0.35
     francese
    0.34
     Leer
    0.34
     for
    0.33
    Activations Density 0.008%

    No Known Activations