Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74273
    Prev
    Next
    INDEX
    Explanations

    Mell

    np_max-act-logits · 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
    Hochspringen
    -0.59
     Lamar
    -0.54
     OFDb
    -0.50
    GEBURTSDATUM
    -0.49
     transfieras
    -0.48
    Expectations
    -0.48
    Lamar
    -0.47
     Miracles
    -0.47
    andExpect
    -0.47
     misunderstand
    -0.47
    POSITIVE LOGITS
    OGND
    0.73
     AssemblyTitle
    0.65
    findpost
    0.56
     Wayback
    0.54
    bank
    0.54
    ướng
    0.52
    kháu
    0.51
    ographic
    0.50
     hashCode
    0.49
     Bradshaw
    0.49
    Activations Density 0.001%

    No Known Activations