© 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. 43725
    Prev
    Next
    INDEX
    Explanations

    link

    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
    ings
    -0.69
    DebuggerStep
    -0.67
    évaluateur
    -0.65
    kegaard
    -0.64
    antaranya
    -0.62
    ends
    -0.61
    lably
    -0.60
     entanto
    -0.60
     Reſ
    -0.60
    ingly
    -0.59
    POSITIVE LOGITS
    RepeatedField
    0.66
     the
    0.57
     all
    0.52
    cusa
    0.49
     EconPapers
    0.48
     an
    0.47
     individual
    0.46
     our
    0.46
    shadowRadius
    0.46
     CommonModule
    0.45
    Activations Density 0.055%

    No Known Activations