© 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. 20-CLT-HP
    7. 73402
    Prev
    Next
    INDEX
    Explanations

    couple

    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
     AssemblyCulture
    -0.89
    TypedDataSet
    -0.75
     CreateTagHelper
    -0.72
    aarrggbb
    -0.68
    webElementXpaths
    -0.67
    édrale
    -0.66
    enterOuterAlt
    -0.65
    OGND
    -0.64
    Демографія
    -0.63
    }],
    -0.62
    POSITIVE LOGITS
     oof
    0.48
     off
    0.48
     fo
    0.47
     AÑOS
    0.43
     OF
    0.42
     oi
    0.42
     ot
    0.41
     anf
    0.41
     Off
    0.40
    ofs
    0.40
    Activations Density 0.000%

    No Known Activations