© 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. 5-CLT-HP
    7. 92746
    Prev
    Next
    INDEX
    Explanations

    high quality; talented

    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
    astéro
    -0.52
     vielen
    -0.48
     démocr
    -0.48
     aikaa
    -0.47
     muuta
    -0.47
     pessoal
    -0.46
     jongen
    -0.45
     recev
    -0.45
     enkelte
    -0.45
     claros
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.85
     незавершена
    0.71
    InputBorder
    0.65
    IntoConstraints
    0.64
    forRoot
    0.62
    
    0.62
    UpInside
    0.61
    TableHead
    0.60
    XmlRootElement
    0.60
    tvguidetime
    0.60
    Activations Density 0.001%

    No Known Activations