© 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. 96318
    Prev
    Next
    INDEX
    Explanations

    park

    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
    AddRange
    -0.52
    []){
    -0.50
    Einzelnachweise
    -0.48
    Ārējās
    -0.46
    Tort
    -0.45
    )}^{
    -0.43
    TabIndex
    -0.42
    usual
    -0.42
     recently
    -0.41
    adilan
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.77
    SourceChecksum
    0.76
    bootstrapcdn
    0.72
    
    0.70
     autorytatywna
    0.68
    ValueStyle
    0.67
     utafitiHapana
    0.66
     scatola
    0.64
     houſe
    0.64
     Meksiku
    0.64
    Activations Density 0.000%

    No Known Activations