© 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. 94015
    Prev
    Next
    INDEX
    Explanations

    math/code formulas

    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
     Heilige
    -0.45
    tiness
    -0.44
    UserScript
    -0.43
    MockBean
    -0.43
    GeV
    -0.43
     coreana
    -0.42
     parchment
    -0.42
     TPR
    -0.42
     tether
    -0.41
    HideFlags
    -0.41
    POSITIVE LOGITS
     препратки
    0.77
     nahilalakip
    0.71
    nokia
    0.63
    tvguidetime
    0.63
     at
    0.59
    ⓧ
    0.58
     Co
    0.56
     Each
    0.55
    favicon
    0.55
     nakalista
    0.54
    Activations Density 0.011%

    No Known Activations