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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96846
    Prev
    Next
    INDEX
    Explanations

    angular

    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
     autorytatywna
    -0.69
     détru
    -0.63
     stället
    -0.62
     rêves
    -0.62
     vœux
    -0.60
     fermés
    -0.59
     الحره
    -0.55
     négociations
    -0.55
     vantagem
    -0.55
     tajam
    -0.55
    POSITIVE LOGITS
    veland
    0.58
     mats
    0.57
     AppColors
    0.52
     dresses
    0.51
     pads
    0.51
    tagHelperRunner
    0.51
    AddWithValue
    0.49
     outfits
    0.49
    bish
    0.49
    apura
    0.49
    Activations Density 0.014%

    No Known Activations