© 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. 5-CLT-HP
    7. 94063
    Prev
    Next
    INDEX
    Explanations

    own

    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
     שוליים
    -0.76
    contentLoaded
    -0.75
    rrggbb
    -0.74
     otomatig
    -0.72
    aarrggbb
    -0.69
     nakalista
    -0.67
    sizeCache
    -0.66
    msgTypes
    -0.66
     препратки
    -0.63
    Lähteet
    -0.63
    POSITIVE LOGITS
     well
    0.56
     self
    0.46
    well
    0.44
     as
    0.42
    merking
    0.41
     wellbeing
    0.40
    Xna
    0.40
    .
    0.40
     good
    0.39
     reduction
    0.39
    Activations Density 0.001%

    No Known Activations