Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11192
    Prev
    Next
    INDEX
    Explanations

    permission

    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
    onViewCreated
    -0.58
    ths
    -0.48
     videre
    -0.47
     perioden
    -0.47
    anță
    -0.47
     esetben
    -0.46
    loyer
    -0.46
     Permission
    -0.46
     spécialistes
    -0.46
    VU
    -0.46
    POSITIVE LOGITS
    хьтан
    0.68
    قایناقلار
    0.65
    /*
    0.57
     "..\..\..\
    0.57
     mapStateToProps
    0.56
    sidemargin
    0.55
    SharedDtor
    0.54
    IVEREF
    0.53
    Mediabestanden
    0.53
    بوابة
    0.53
    Activations Density 0.009%

    No Known Activations