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. 20-CLT-HP
    4. 74040
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · 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
    .
    -0.68
    ٫
    -0.65
     chré
    -0.53
    (;;)
    -0.49
     SafeMath
    -0.48
     apellidos
    -0.45
     chiesto
    -0.45
     fondament
    -0.45
     déchir
    -0.45
     paraître
    -0.44
    POSITIVE LOGITS
    5
    0.77
    4
    0.73
    3
    0.73
     الحره
    0.73
    2
    0.72
    7
    0.71
    6
    0.71
    8
    0.71
    9
    0.68
    1
    0.67
    Activations Density 0.013%

    No Known Activations