© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93120
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    
    -0.51
    Evet
    -0.41
    ही
    -0.41
     Stretching
    -0.39
     خود
    -0.39
     des
    -0.38
    ban
    -0.37
    切
    -0.37
    のである
    -0.36
     xếp
    -0.36
    POSITIVE LOGITS
    +#+#
    0.98
     تضيفلها
    0.98
    expandindo
    0.96
    ThroughAttribute
    0.94
    DebuggerNonUser
    0.92
    findpost
    0.90
     للمعارف
    0.88
    NewUrlParser
    0.85
    الحياه
    0.82
    tagHelperRunner
    0.82
    Activations Density 0.001%

    No Known Activations