© 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. 0-CLT-HP
    7. 93050
    Prev
    Next
    INDEX
    Explanations

    tin

    np_max-act · 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
     tin
    -1.62
    tin
    -1.51
    Tin
    -1.27
     Tin
    -1.26
     clue
    -1.20
     clues
    -1.11
     TIN
    -0.95
    TIN
    -0.91
     Clue
    -0.86
    Clue
    -0.84
    POSITIVE LOGITS
     Wikimedijinoj
    0.69
    bootstrapcdn
    0.69
    rrggbb
    0.66
    ParallelGroup
    0.60
     nahilalakip
    0.60
     kaarangay
    0.59
     Nell
    0.56
     Hendrix
    0.56
    kháu
    0.55
    ful
    0.53
    Activations Density 0.140%

    No Known Activations