© 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. 990
    Prev
    Next
    INDEX
    Explanations

    seamless, smooth

    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
     isolada
    -0.60
    Uhr
    -0.55
    Hochspringen
    -0.53
     consacré
    -0.52
    TypedDataSet
    -0.52
    emailAddress
    -0.51
     quête
    -0.50
     célèbres
    -0.49
     prière
    -0.49
     remarquer
    -0.49
    POSITIVE LOGITS
     integration
    0.84
     transition
    0.77
     hand
    0.75
     Hand
    0.71
     blend
    0.71
    Hand
    0.68
     integrate
    0.68
     handover
    0.68
     otomatig
    0.67
    hand
    0.66
    Activations Density 0.001%

    No Known Activations