© 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. 73777
    Prev
    Next
    INDEX
    Explanations

    Programming syntax

    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
     مُعرِّف
    -0.63
     pinulongan
    -0.63
    Datuak
    -0.60
     محفوظة
    -0.56
    fromnode
    -0.56
    पि
    -0.55
    GEBURTSDATUM
    -0.52
     chi̍t
    -0.51
    IVEREF
    -0.50
    OutputType
    -0.50
    POSITIVE LOGITS
    contentLoaded
    0.55
    τως
    0.49
     kasarigan
    0.49
    Revenir
    0.48
    外部リンク
    0.47
    (!__
    0.46
    ValueStyle
    0.46
     Geraadpleegd
    0.45
     betweenstory
    0.45
    enumi
    0.45
    Activations Density 0.003%

    No Known Activations