© 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. 92055
    Prev
    Next
    INDEX
    Explanations

    conditional/contrast statements

    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
     BrowserModule
    -0.75
     noDo
    -0.71
    tvguidetime
    -0.69
    mybatisplus
    -0.68
    หวัด
    -0.68
    DockStyle
    -0.66
     AssemblyCulture
    -0.62
    popd
    -0.59
    LookAnd
    -0.59
    脚注の使い方
    -0.59
    POSITIVE LOGITS
     none
    0.41
    S
    0.41
     ничего
    0.40
    P
    0.40
     rewarded
    0.40
     None
    0.38
     congru
    0.38
     refle
    0.36
    setcounter
    0.36
     contem
    0.36
    Activations Density 0.006%

    No Known Activations