© 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. 41198
    Prev
    Next
    INDEX
    Explanations

    new

    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
    lihatkan
    -0.56
     cerimonia
    -0.56
    adaptiveStyles
    -0.54
    lijck
    -0.53
     bepaalde
    -0.52
     varandra
    -0.51
    cakup
    -0.50
     antigüedad
    -0.50
     bersih
    -0.50
     illustrazione
    -0.49
    POSITIVE LOGITS
    IZONA
    0.58
    نگار
    0.57
    prüche
    0.57
     DNA
    0.55
     homeland
    0.54
     basis
    0.54
    XmlAccessType
    0.54
    VAO
    0.54
     pas
    0.53
    imeter
    0.53
    Activations Density 0.113%

    No Known Activations