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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5271
    Prev
    Next
    INDEX
    Explanations

    programming/data challenges

    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
     насељу
    -0.46
     становника
    -0.43
    ]--;
    -0.40
     Mills
    -0.37
    zuk
    -0.35
    开发者
    -0.35
     hawa
    -0.34
     oportunidad
    -0.34
     obstante
    -0.34
     oportunidade
    -0.33
    POSITIVE LOGITS
    enumii
    0.69
    انيف
    0.67
     numberWith
    0.65
    ("'"
    0.64
    rceil
    0.63
     belong
    0.61
     forKey
    0.61
     xlink
    0.59
     jLabel
    0.59
    transQ
    0.59
    Activations Density 0.077%

    No Known Activations