© 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. 0-CLT-HP
    7. 43520
    Prev
    Next
    INDEX
    Explanations

    Forbidden

    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
     Forbidden
    -1.40
    Forbidden
    -0.89
    \{\\
    -0.71
     ainfi
    -0.59
    mybatisplus
    -0.58
     normaux
    -0.57
    forbidden
    -0.56
     Deber
    -0.56
    ändigkeit
    -0.56
     resistenza
    -0.55
    POSITIVE LOGITS
     City
    0.56
    ly
    0.55
     Fru
    0.54
    تقاوى
    0.54
    <bos>
    0.52
    atories
    0.52
    kaŭ
    0.51
    ALAND
    0.50
    wixt
    0.50
    iously
    0.49
    Activations Density 0.070%

    No Known Activations