© 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. 40445
    Prev
    Next
    INDEX
    Explanations

    recent information

    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
    ateness
    -0.96
    urally
    -0.70
     insider
    -0.67
    Insider
    -0.65
    rofoam
    -0.64
    masing
    -0.64
     éducation
    -0.63
     Arrondissement
    -0.62
     pinulongan
    -0.61
    fillType
    -0.61
    POSITIVE LOGITS
    \{\\
    0.49
    thy
    0.47
    Fac
    0.42
     taken
    0.42
    ity
    0.42
    '
    0.41
    ArrowToggle
    0.40
    EndContext
    0.40
    pyplot
    0.40
    ’
    0.40
    Activations Density 0.215%

    No Known Activations