© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40806
    Prev
    Next
    INDEX
    Explanations

    mean

    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
     mean
    -1.02
    ide
    -0.91
     surla
    -0.66
    IDE
    -0.63
    mean
    -0.54
    — 
    -0.53
    ütü
    -0.52
     ideal
    -0.51
    bara
    -0.49
     MEAN
    -0.48
    POSITIVE LOGITS
     Diſ
    0.68
     coherence
    0.66
     ſche
    0.64
     Anſ
    0.63
     Reſ
    0.61
     purpoſe
    0.61
     fubject
    0.60
     pleaſure
    0.60
     Monfieur
    0.60
     tartalomajánló
    0.60
    Activations Density 0.031%

    No Known Activations