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. 11305
    Prev
    Next
    INDEX
    Explanations

    normal

    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
    endphp
    -0.61
    DockStyle
    -0.56
     ligiloj
    -0.51
    beginTransaction
    -0.49
    erialize
    -0.49
    #+#
    -0.48
    astéroïdes
    -0.48
    culosis
    -0.48
     Савезне
    -0.48
    +#+
    -0.48
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.70
     صوتيه
    0.54
     mum
    0.53
    lamy
    0.52
    chor
    0.50
     tep
    0.50
    foreignKey
    0.49
    stos
    0.48
    Authors
    0.48
    amy
    0.47
    Activations Density 0.036%

    No Known Activations