© 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. 0-CLT-HP
    7. 95057
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     feroit
    -1.17
     auroit
    -1.17
     étoient
    -1.16
     avoient
    -1.16
     pouvoit
    -1.09
     démocr
    -1.07
    tvguidetime
    -1.05
     enfans
    -1.05
     zelve
    -1.05
     étoit
    -1.03
    POSITIVE LOGITS
    <bos>
    1.41
    ↵
    1.27
    '
    1.25
    ↵↵
    1.17
     "
    1.14
    "
    1.12
    ’
    1.11
     '
    1.06
     “
    1.03
     
    0.98
    Activations Density 44.975%

    No Known Activations