© 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. 96176
    Prev
    Next
    INDEX
    Explanations

    Ease and difficulty

    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
    ✨:
    -0.79
     utafitiHapana
    -0.78
     surla
    -0.78
    Geplaatst
    -0.77
    IContainer
    -0.73
    tvguidetime
    -0.71
    doria
    -0.70
     समीक्षक
    -0.68
    enumii
    -0.68
    yntaxException
    -0.68
    POSITIVE LOGITS
     to
    0.98
     (
    0.56
     for
    0.52
     saada
    0.47
     élevés
    0.46
     récents
    0.45
    capt
    0.45
     getting
    0.44
    copg
    0.44
     transferir
    0.42
    Activations Density 0.004%

    No Known Activations