© 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. 0-CLT-HP
    7. 94421
    Prev
    Next
    INDEX
    Explanations

    continuous

    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
     continuous
    -1.91
     Continuous
    -1.70
    Continuous
    -1.70
    continuous
    -1.68
     continuously
    -1.13
     contín
    -1.13
     continual
    -0.95
     kontinuier
    -0.95
     discontinuous
    -0.90
    连续
    -0.89
    POSITIVE LOGITS
    Coordenadas
    0.61
    NameInMap
    0.60
    évaluateur
    0.60
     '\\;'
    0.60
    Tikang
    0.57
     سكانية
    0.56
    _));
    0.54
     MessageBoxIcon
    0.54
     intStringLen
    0.54
    Portale
    0.52
    Activations Density 1.063%

    No Known Activations