© 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. 5-CLT-HP
    7. 5867
    Prev
    Next
    INDEX
    Explanations

    code strings

    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
     nahilalakip
    -0.69
    AddHtmlAttribute
    -0.69
     TextAppearance
    -0.69
    脚注の使い方
    -0.67
    __(/*!
    -0.66
     Signalez
    -0.66
     "..\..\..\
    -0.65
    цездатний
    -0.63
     WQS
    -0.63
     autorytatywna
    -0.62
    POSITIVE LOGITS
     hind
    0.62
     bulk
    0.59
     hinder
    0.57
     hin
    0.57
     bush
    0.51
    hind
    0.51
     congestion
    0.48
     hol
    0.48
     hindrance
    0.46
     rep
    0.46
    Activations Density 0.001%

    No Known Activations