© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2105
    Prev
    Next
    INDEX
    Explanations

    animal

    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
    ParallelGroup
    -0.59
    ftagPool
    -0.59
     ***!
    -0.54
     وتسجيلات
    -0.54
     ExecuteAsync
    -0.51
    TagMode
    -0.51
     Brem
    -0.50
    AnimationsModule
    -0.50
    EReference
    -0.49
     maat
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.60
    Šaltiniai
    0.50
     shrugged
    0.49
    enservice
    0.48
    ])):
    0.48
    inafter
    0.47
    Liefs
    0.47
    ])));
    0.47
    لها
    0.46
    Beijinhos
    0.45
    Activations Density 0.000%

    No Known Activations