© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72997
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    np_max-act-logits · 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
    ########.
    -0.67
    !*\
    -0.60
    PreferredItem
    -0.54
     []:
    -0.52
    scriptcase
    -0.50
     class
    -0.49
    :+:
    -0.49
    ::::::::
    -0.48
    DOCTYPE
    -0.47
    NameValuePair
    -0.44
    POSITIVE LOGITS
     arrivant
    0.53
    >{@
    0.52
    Biographie
    0.52
     Campion
    0.52
    日閲覧
    0.52
    IsContent
    0.51
    Altri
    0.50
     استنادى
    0.50
     mukaan
    0.49
     kokona
    0.49
    Activations Density 0.000%

    No Known Activations