© 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. 94651
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    aco
    -0.76
    SequentialGroup
    -0.66
    persed
    -0.65
    numerusform
    -0.59
    isman
    -0.54
    
    -0.52
    HasAnnotation
    -0.50
    ImageContext
    -0.50
     consultato
    -0.50
    Abstra
    -0.49
    POSITIVE LOGITS
     Charlemagne
    0.62
     MediaType
    0.61
     condem
    0.60
     $_"
    0.58
     Justo
    0.58
     tartalomajánló
    0.58
    ContentAsync
    0.57
     cruc
    0.56
    iritto
    0.56
     Examen
    0.55
    Activations Density 0.227%

    No Known Activations