© 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. 15149
    Prev
    Next
    INDEX
    Explanations

    code and punctuation

    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
    InjectAttribute
    -0.78
     "..\..\..\
    -0.60
    TypedDataSet
    -0.59
     let
    -0.57
    addContainerGap
    -0.56
    contentLoaded
    -0.55
     estimés
    -0.55
    thday
    -0.55
     on
    -0.54
     "..\..\
    -0.54
    POSITIVE LOGITS
     agujeros
    0.52
    vlá
    0.52
     détru
    0.51
     avulla
    0.51
     umana
    0.50
     giù
    0.49
     sáb
    0.47
     mourut
    0.46
     étr
    0.46
     varandra
    0.46
    Activations Density 0.004%

    No Known Activations