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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93101
    Prev
    Next
    INDEX
    Explanations

    clones

    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
    back
    -0.58
     تضيفلها
    -0.50
    )++;
    -0.43
    base
    -0.42
    y
    -0.41
    -
    -0.41
    -0.40
    client
    -0.39
     tī
    -0.39
     mimo
    -0.38
    POSITIVE LOGITS
     يتيمه
    0.74
     للمعارف
    0.70
     ibid
    0.69
    initComponents
    0.69
     hexadecimal
    0.68
     automatiques
    0.68
    PositiveButton
    0.67
    UrlEncoded
    0.66
    isContained
    0.65
    cyd
    0.65
    Activations Density 0.394%

    No Known Activations