© 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. 10302
    Prev
    Next
    INDEX
    Explanations

    stability

    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
     COMM
    -0.45
     становника
    -0.43
    tead
    -0.43
    INST
    -0.42
     stabilizing
    -0.42
     stabili
    -0.41
    iburg
    -0.41
    乏
    -0.40
    freude
    -0.40
    chaik
    -0.40
    POSITIVE LOGITS
    
    0.71
    SPATH
    0.69
    MockBean
    0.69
    ViewImports
    0.69
     AttributeSet
    0.68
    momix
    0.63
    HtmlAttribute
    0.63
     незавершена
    0.62
    Ссылки
    0.60
    Lähteet
    0.60
    Activations Density 0.092%

    No Known Activations