© 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. 0-CLT-HP
    7. 91944
    Prev
    Next
    INDEX
    Explanations

    continuity

    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
    Continuous
    -1.20
     continuous
    -1.09
    continuous
    -1.09
     Continuous
    -1.06
     continuity
    -1.04
     kontinu
    -1.04
     Continuity
    -1.01
    Continuity
    -0.95
     throughout
    -0.92
     continuidad
    -0.92
    POSITIVE LOGITS
    ly
    0.66
    LookAnd
    0.63
    ness
    0.63
    es
    0.55
    nya
    0.52
     Ur
    0.52
     Ung
    0.51
    ner
    0.50
    LY
    0.50
    en
    0.49
    Activations Density 0.081%

    No Known Activations