© 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. 1-CLT-HP
    7. 12051
    Prev
    Next
    INDEX
    Explanations

    give

    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
    aarrggbb
    -0.73
     AssemblyCulture
    -0.69
    contentLoaded
    -0.59
     Signalez
    -0.59
    Geplaatst
    -0.55
     الدولى
    -0.54
    posedge
    -0.54
     StatelessWidget
    -0.54
    Kilder
    -0.53
    basicConfig
    -0.53
    POSITIVE LOGITS
     thanks
    0.60
    LinkId
    0.49
     sight
    0.48
    Es
    0.46
     judgement
    0.46
     Tob
    0.45
    principalTable
    0.44
     freely
    0.44
     viewType
    0.43
     judgment
    0.43
    Activations Density 0.008%

    No Known Activations