© 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. 5-CLT-HP
    7. 94164
    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
    co
    -0.47
    an
    -0.43
     C
    -0.42
    los
    -0.42
     H
    -0.41
     Lewis
    -0.41
    gi
    -0.40
     sklo
    -0.39
    drawSprites
    -0.39
     O
    -0.39
    POSITIVE LOGITS
    DockStyle
    1.08
    ChildScrollView
    0.91
     للمعارف
    0.88
     يتيمه
    0.88
     تضيفلها
    0.85
     doInBackground
    0.84
     itſelf
    0.83
     Efq
    0.83
    ConstraintMaker
    0.81
     invokingState
    0.80
    Activations Density 0.000%

    No Known Activations