© 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. 0-CLT-HP
    7. 41779
    Prev
    Next
    INDEX
    Explanations

    cate

    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
    iffance
    -1.20
    encils
    -1.15
    æus
    -1.12
    ipheral
    -1.10
    hematical
    -1.09
    uſe
    -1.09
    ratulations
    -1.08
    gnition
    -1.05
    vrolet
    -1.05
    polation
    -1.02
    POSITIVE LOGITS
    ly
    0.79
     Idy
    0.79
    y
    0.78
    li
    0.77
    co
    0.76
    ty
    0.76
    j
    0.76
    son
    0.75
    ten
    0.74
     Esau
    0.74
    Activations Density 0.160%

    No Known Activations