© 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. 4-CLT-HP
    7. 834
    Prev
    Next
    INDEX
    Explanations

    punctuation and conversation snippets

    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
    mpä
    -0.60
    Autoritní
    -0.59
     posters
    -0.52
     liefer
    -0.50
     women
    -0.50
     mine
    -0.50
     positive
    -0.50
    ياه
    -0.49
     marine
    -0.49
     mines
    -0.49
    POSITIVE LOGITS
    NameInMap
    0.71
    MemoryWarning
    0.68
    الحياه
    0.66
    ThroughAttribute
    0.62
    شهاد
    0.57
     Normdatei
    0.55
     UIAlert
    0.54
    HomeAsUpEnabled
    0.52
    InputBorder
    0.52
    ModelSerializer
    0.52
    Activations Density 0.012%

    No Known Activations