© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13935
    Prev
    Next
    INDEX
    Explanations

    alternate

    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
    alternative
    -0.62
     alternative
    -0.60
    Alternative
    -0.60
     transfieras
    -0.60
     autorytatywna
    -0.56
    Alternate
    -0.56
     Alternative
    -0.56
    !*\
    -0.55
    altern
    -0.53
    webElementXpaths
    -0.53
    POSITIVE LOGITS
     keyboards
    0.54
     Biro
    0.52
     account
    0.50
     subtraction
    0.50
     costumes
    0.49
     scoreboard
    0.49
    })();
    0.49
    tometer
    0.48
     fairest
    0.48
     Account
    0.47
    Activations Density 0.034%

    No Known Activations