© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4317
    Prev
    Next
    INDEX
    Explanations

    stages or phases

    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
     lenker
    -0.82
    SBATCH
    -0.79
    zköz
    -0.71
    MENAFN
    -0.67
     ویکی‌پدیا
    -0.66
    dafx
    -0.65
    Aktualisiert
    -0.64
     piedi
    -0.64
    photobucket
    -0.63
    Източници
    -0.63
    POSITIVE LOGITS
    t
    0.44
    tsu
    0.44
    EN
    0.44
     переписи
    0.42
    ERN
    0.41
     Response
    0.40
     tu
    0.40
    Vla
    0.40
     es
    0.39
     intentionally
    0.37
    Activations Density 0.001%

    No Known Activations