© 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. 96444
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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
    OGND
    -0.85
     HasFactory
    -0.82
     betweenstory
    -0.79
     nahilalakip
    -0.77
     مشين
    -0.77
     виправивши
    -0.74
    FontOfSize
    -0.74
     Administrativna
    -0.72
    tagHelperRunner
    -0.71
     Monfieur
    -0.71
    POSITIVE LOGITS
    .
    0.53
    ,
    0.53
     set
    0.50
    hassee
    0.47
    serializers
    0.46
     Set
    0.45
     witnesses
    0.44
     condition
    0.43
    chrän
    0.43
     being
    0.42
    Activations Density 0.003%

    No Known Activations