© 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. 4-CLT-HP
    7. 4733
    Prev
    Next
    INDEX
    Explanations

    explain

    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
     GenerationType
    -0.57
     Dostupné
    -0.55
     AppCompatTheme
    -0.54
     [*]
    -0.53
    ureusement
    -0.50
    SequentialGroup
    -0.50
    StreetMap
    -0.50
    LookAnd
    -0.49
    stens
    -0.48
    sterious
    -0.48
    POSITIVE LOGITS
     simply
    0.96
    simply
    0.94
    Simply
    0.91
     Simply
    0.88
     simplement
    0.69
     visually
    0.68
     thoroughly
    0.66
     simplemente
    0.66
     Simplemente
    0.65
     jednod
    0.65
    Activations Density 0.004%

    No Known Activations