© 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. 75537
    Prev
    Next
    INDEX
    Explanations

    say "th" words

    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
    ])):
    -0.64
    esgue
    -0.63
     arşivlendi
    -0.60
    WriteBarrier
    -0.58
     bianca
    -0.58
     Jodi
    -0.56
     UIFont
    -0.55
     Midtown
    -0.55
     Sequel
    -0.54
    seln
    -0.54
    POSITIVE LOGITS
    th
    0.54
     resourceCulture
    0.54
    principalColumn
    0.54
    ایج
    0.53
    pertory
    0.48
     betrieben
    0.44
    Born
    0.44
    ExtendWith
    0.44
     portato
    0.42
     olev
    0.42
    Activations Density 0.014%

    No Known Activations