© 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. 1-CLT-HP
    7. 15282
    Prev
    Next
    INDEX
    Explanations

    scientific analysis/coding

    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
    vitational
    -0.57
    flage
    -0.57
    älde
    -0.56
    +#+
    -0.56
    ClientSize
    -0.52
    antly
    -0.51
    Історія
    -0.50
    CloseOperation
    -0.50
    FontStyle
    -0.50
     AttributeSet
    -0.50
    POSITIVE LOGITS
    ChildScrollView
    0.68
    liesslich
    0.52
    ioutil
    0.52
    országban
    0.47
    '){
    0.46
    ztály
    0.46
    MemoryWarning
    0.46
    ]){
    0.45
     rev
    0.45
    ()){
    0.44
    Activations Density 0.151%

    No Known Activations