© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11613
    Prev
    Next
    INDEX
    Explanations

    sibly

    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
     kaarangay
    -0.66
    ,:);
    -0.61
    ellido
    -0.58
     utafitiHapana
    -0.54
    thâu
    -0.54
    TestTools
    -0.53
    aguya
    -0.53
    Personendaten
    -0.52
     gainera
    -0.51
    manded
    -0.50
    POSITIVE LOGITS
    ParallelGroup
    0.58
     ويكيميديا
    0.53
    ViewFeatures
    0.51
    Format
    0.51
     raken
    0.50
    UnknownFields
    0.48
    format
    0.48
    Clik
    0.47
    CJK
    0.47
     formato
    0.46
    Activations Density 0.015%

    No Known Activations