© 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. 1-CLT-HP
    7. 46061
    Prev
    Next
    INDEX
    Explanations

    words

    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
    Viitteet
    -0.70
     words
    -0.65
     word
    -0.57
     Stability
    -0.56
     kommentar
    -0.51
     stability
    -0.50
     précisé
    -0.48
     STABILITY
    -0.47
     Speicher
    -0.47
     متعلقه
    -0.47
    POSITIVE LOGITS
     Rosh
    0.60
    arian
    0.57
     Phoen
    0.56
    sterious
    0.55
    >{@
    0.52
     Moslem
    0.52
     Tant
    0.52
     Audiodateien
    0.51
    ẳng
    0.51
    ingly
    0.51
    Activations Density 0.005%

    No Known Activations