© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74946
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific text

    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
    tvguidetime
    -0.88
    SBATCH
    -0.76
    NewUrlParser
    -0.75
    AddHtmlAttribute
    -0.73
     Италијани
    -0.72
    Geplaatst
    -0.69
    ArgsConstructor
    -0.69
    ніципа
    -0.69
    webElementXpaths
    -0.68
    offsetof
    -0.66
    POSITIVE LOGITS
    net
    0.40
     elétrico
    0.39
    BagLayout
    0.38
     secours
    0.37
    cels
    0.35
    Bly
    0.35
     Blue
    0.35
    dor
    0.34
    et
    0.34
     bleue
    0.34
    Activations Density 0.034%

    No Known Activations