© 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. 5-CLT-HP
    7. 3058
    Prev
    Next
    INDEX
    Explanations

    4 or 6

    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
     BorderRadius
    -0.56
    InjectAttribute
    -0.53
    NamedQueries
    -0.48
     برانيه
    -0.48
    ThroughAttribute
    -0.45
     يتيمه
    -0.45
    AZINE
    -0.44
    Eight
    -0.44
    ાય
    -0.44
    ReusableCell
    -0.44
    POSITIVE LOGITS
    totic
    0.58
     Elke
    0.52
    íslu
    0.51
    ỡ
    0.51
     Palgrave
    0.50
     '\\;'
    0.50
    casm
    0.50
    ETO
    0.50
    elf
    0.49
    elski
    0.49
    Activations Density 0.015%

    No Known Activations