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. 10996
    Prev
    Next
    INDEX
    Explanations

    Brotherhood

    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
    StoryboardSegue
    -0.61
     Brotherhood
    -0.61
    Brother
    -0.59
     huiles
    -0.57
    ragamo
    -0.50
     dureza
    -0.50
     proprietà
    -0.50
    ExtendWith
    -0.48
     Brother
    -0.48
     brotherhood
    -0.48
    POSITIVE LOGITS
    Pautan
    0.60
    ülé
    0.55
    abestanden
    0.53
    *}$
    0.53
    rifuge
    0.53
    衅
    0.52
    ruptedException
    0.52
    nóstico
    0.52
    zyp
    0.51
    getLatitude
    0.50
    Activations Density 0.119%

    No Known Activations