© 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. 3385
    Prev
    Next
    INDEX
    Explanations

    FDA

    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
     position
    -0.42
    TargetException
    -0.41
    UnsafeEnabled
    -0.41
    otide
    -0.39
    astéro
    -0.38
    __;
    -0.38
     up
    -0.38
     trans
    -0.38
     t
    -0.38
     Ep
    -0.37
    POSITIVE LOGITS
     otomatig
    0.76
     تكبرها
    0.68
     barnen
    0.66
     varandra
    0.60
     chré
    0.60
     anciennes
    0.59
     bénéfices
    0.59
     länge
    0.59
     considér
    0.59
     själ
    0.59
    Activations Density 0.008%

    No Known Activations