© 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. 20-CLT-HP
    7. 76678
    Prev
    Next
    INDEX
    Explanations

    configuration/code

    np_max-act-logits · 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
    antMatchers
    -0.59
     contenuto
    -0.54
    ⓧ
    -0.52
     verrez
    -0.52
     communautaire
    -0.51
    tagext
    -0.48
    SerializedSize
    -0.47
     Corbett
    -0.46
    Carriera
    -0.45
    ตร์
    -0.45
    POSITIVE LOGITS
     contacts
    0.69
    참고
    0.66
    Izvori
    0.64
    Примітки
    0.60
     Contacts
    0.59
    misu
    0.57
    Solr
    0.57
     Blinds
    0.55
    ONSORED
    0.54
    contacts
    0.54
    Activations Density 0.001%

    No Known Activations