© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43712
    Prev
    Next
    INDEX
    Explanations

    tro, cytos

    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
    SourceChecksum
    -0.94
    tagHelperRunner
    -0.90
     InputDecoration
    -0.79
    ſelf
    -0.78
    bootstrapcdn
    -0.76
     uſed
    -0.76
    Übernach
    -0.75
    Vidite
    -0.75
    tro
    -0.74
    thâu
    -0.72
    POSITIVE LOGITS
     arşivlendi
    0.44
    ff
    0.42
    op
    0.40
    ('|
    0.40
    ops
    0.39
    FF
    0.39
     deep
    0.38
     circo
    0.37
    deep
    0.36
     Tor
    0.36
    Activations Density 0.026%

    No Known Activations