© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9090
    Prev
    Next
    INDEX
    Explanations

    culture and official announcements

    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
     Francesca
    -0.63
    onnaise
    -0.47
    ícil
    -0.46
     courants
    -0.45
     japonais
    -0.44
     présidenti
    -0.43
    umumkan
    -0.43
    IDER
    -0.42
    Šaltiniai
    -0.41
     acompañado
    -0.41
    POSITIVE LOGITS
    OGND
    0.76
    DeleteBehavior
    0.75
     Signalez
    0.75
    IsContent
    0.72
    featureID
    0.68
    sizeCache
    0.68
    曖昧さ回避
    0.68
    oa̍t
    0.67
    TagMode
    0.66
    NewUrlParser
    0.65
    Activations Density 0.030%

    No Known Activations