© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1916
    Prev
    Next
    INDEX
    Explanations

    home/leisure

    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
     disambiguazione
    -1.34
     itſelf
    -1.33
     Efq
    -1.18
     myſelf
    -1.15
    RenderAtEndOf
    -1.09
     Normdatei
    -1.07
     Majefty
    -1.05
    ViewFeatures
    -1.05
     Shakspeare
    -1.05
     CreateTagHelper
    -1.04
    POSITIVE LOGITS
    .
    0.68
    ,
    0.66
     
    0.59
     and
    0.57
     a
    0.56
     are
    0.56
    :
    0.53
     (
    0.51
     for
    0.50
    ;
    0.50
    Activations Density 0.740%

    No Known Activations