© 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. 38276
    Prev
    Next
    INDEX
    Explanations

    pertaining

    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
    chengladbach
    -0.60
    EDEFAULT
    -0.59
    twimg
    -0.56
    גרת
    -0.54
    brainly
    -0.53
    thane
    -0.51
    Посилання
    -0.51
    الإنجليزية
    -0.50
    tale
    -0.50
    WaitGroup
    -0.49
    POSITIVE LOGITS
     reaſon
    0.93
     ſtate
    0.86
     houſe
    0.86
     purpoſe
    0.86
     Monfieur
    0.83
     ſtand
    0.81
     ſever
    0.81
     ſmall
    0.79
     miſ
    0.76
     ſtill
    0.76
    Activations Density 0.104%

    No Known Activations