© 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. 826
    Prev
    Next
    INDEX
    Explanations

    Japanese and programming

    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
    .
    -0.57
     TextAppearance
    -0.50
     ...
    -0.50
     â
    -0.48
     (
    -0.45
     L
    -0.45
     et
    -0.44
     c
    -0.44
     C
    -0.43
     '
    -0.43
    POSITIVE LOGITS
     houſe
    0.81
     ſeveral
    0.81
     purpoſe
    0.76
     chofe
    0.73
     ſmall
    0.73
     Houſe
    0.72
     uſe
    0.72
     raiſ
    0.71
     faſt
    0.71
     ſtate
    0.70
    Activations Density 0.020%

    No Known Activations