© 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. 960
    Prev
    Next
    INDEX
    Explanations

    References to past things

    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
     chré
    -0.70
    horabuena
    -0.69
    bootstrapcdn
    -0.66
     وتسجيلات
    -0.60
     debout
    -0.60
     préoccup
    -0.60
     considér
    -0.59
     sanitaires
    -0.59
    Tazama
    -0.59
    luiting
    -0.58
    POSITIVE LOGITS
    -
    0.62
     acquired
    0.52
     concluded
    0.49
     proved
    0.46
     paid
    0.46
     passed
    0.45
    -“
    0.45
     published
    0.45
    oprene
    0.44
     learned
    0.44
    Activations Density 0.001%

    No Known Activations