© 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. 76850
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
    tagHelperRunner
    -0.92
    ftagPool
    -0.88
    :✨
    -0.77
     transfieras
    -0.75
     invokingState
    -0.74
    ioutil
    -0.72
    Datuak
    -0.71
    IUrlHelper
    -0.71
    Organisateur
    -0.70
     nahilalakip
    -0.69
    POSITIVE LOGITS
    genstein
    0.40
    adecimal
    0.39
    őd
    0.39
     körül
    0.38
    Endian
    0.38
     long
    0.38
     abend
    0.36
     réessayer
    0.36
    depan
    0.35
    MENAFN
    0.35
    Activations Density 0.000%

    No Known Activations