© 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. 0-CLT-HP
    7. 38294
    Prev
    Next
    INDEX
    Explanations

    goals/intentions

    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
    IntoConstraints
    -0.85
    eradish
    -0.81
     aim
    -0.80
    MethodManager
    -0.70
     ComVisible
    -0.68
    FieldBuilder
    -0.68
    tvguidetime
    -0.67
     draft
    -0.67
     незавершена
    -0.66
     &___
    -0.65
    POSITIVE LOGITS
    psie
    0.47
    ant
    0.46
    INIT
    0.44
    cshtml
    0.42
    able
    0.42
    skate
    0.42
    óság
    0.41
    ENI
    0.41
    outé
    0.41
    числен
    0.41
    Activations Density 0.051%

    No Known Activations