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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12694
    Prev
    Next
    INDEX
    Explanations

    patents and "Pat" mentions

    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
    ConstraintMaker
    -0.70
    CppMethod
    -0.63
     jelly
    -0.56
     Jelly
    -0.54
     téléphonique
    -0.46
     quelcon
    -0.45
     addSubview
    -0.44
     Buat
    -0.44
    Jelly
    -0.44
    ätz
    -0.44
    POSITIVE LOGITS
     Administrativna
    0.57
    rami
    0.56
    ropo
    0.55
     Combs
    0.55
    rics
    0.54
    __((
    0.54
    ness
    0.54
    scape
    0.52
    Coordonnées
    0.51
    caris
    0.51
    Activations Density 0.012%

    No Known Activations