© 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. 3003
    Prev
    Next
    INDEX
    Explanations

    avoidance

    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
    seamnă
    -0.78
     itſelf
    -0.76
     ujednoznacz
    -0.74
     ་་
    -0.72
    errHandler
    -0.71
     CreateTagHelper
    -0.71
    NUMX
    -0.70
     myſelf
    -0.69
     Jefus
    -0.67
    nhung
    -0.67
    POSITIVE LOGITS
     all
    0.91
     it
    0.63
    all
    0.61
     or
    0.60
     as
    0.58
     both
    0.53
     every
    0.52
     ALL
    0.52
    .
    0.48
    /
    0.47
    Activations Density 0.001%

    No Known Activations