© 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. 46286
    Prev
    Next
    INDEX
    Explanations

    lie

    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
    tagHelperRunner
    -0.99
     quæ
    -0.63
    +#+#
    -0.62
     Utile
    -0.59
     raiſ
    -0.58
    IsMutable
    -0.56
     ejus
    -0.56
     Taken
    -0.56
     juſt
    -0.56
     eorum
    -0.53
    POSITIVE LOGITS
    rungsseite
    0.53
    tvguidetime
    0.53
    олові
    0.48
    รร
    0.47
    icamente
    0.47
    zend
    0.46
    zeugen
    0.45
    leng
    0.44
    лён
    0.43
    UnsafeEnabled
    0.43
    Activations Density 0.018%

    No Known Activations