© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97350
    Prev
    Next
    INDEX
    Explanations

    events or reports

    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
     prior
    -0.52
    ific
    -0.51
     previous
    -0.50
     grand
    -0.47
     mag
    -0.46
    лега
    -0.44
     W
    -0.44
     مرئيه
    -0.44
     D
    -0.43
    mig
    -0.43
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.74
     pleaſure
    0.65
     fubject
    0.60
     Andante
    0.59
     nahilalakip
    0.59
    
    0.58
     ↓,
    0.58
    requestCode
    0.58
     houſe
    0.58
     Bellow
    0.57
    Activations Density 0.010%

    No Known Activations