© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40259
    Prev
    Next
    INDEX
    Explanations

    adapting

    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
    tical
    -0.66
    netje
    -0.57
    wild
    -0.55
    ist
    -0.54
    less
    -0.50
    net
    -0.49
    name
    -0.48
    ting
    -0.47
    ng
    -0.47
    ists
    -0.46
    POSITIVE LOGITS
    makeConstraints
    0.88
     AttributeSet
    0.80
    oredCriteria
    0.79
     NavController
    0.77
     propOrder
    0.73
    ConstraintMaker
    0.72
     виправивши
    0.71
    StoryboardSegue
    0.71
    argout
    0.69
    yntaxException
    0.68
    Activations Density 0.143%

    No Known Activations