© 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. 20-CLT-HP
    7. 76946
    Prev
    Next
    INDEX
    Explanations

    land

    np_max-act-logits · 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
     Majefty
    -0.71
     purpoſe
    -0.65
     Conſ
    -0.63
     Eſ
    -0.62
    reportWebVitals
    -0.60
     Diſ
    -0.59
     FontWeight
    -0.59
     zelve
    -0.59
     disambiguazione
    -0.59
    ConstraintMaker
    -0.57
    POSITIVE LOGITS
     y
    0.56
    ----</
    0.54
     AssemblyCulture
    0.52
     Ro
    0.52
     ro
    0.51
     speed
    0.49
    whale
    0.48
    Ro
    0.47
     na
    0.47
     Speed
    0.46
    Activations Density 0.000%

    No Known Activations