© 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. 40613
    Prev
    Next
    INDEX
    Explanations

    Soy and border crossings

    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
     crossings
    -0.75
    matory
    -0.57
    Portail
    -0.56
     Soy
    -0.55
     soy
    -0.52
    ]")]
    -0.51
     ſte
    -0.51
     ſch
    -0.50
    fă
    -0.48
     못
    -0.48
    POSITIVE LOGITS
    تقاوى
    0.85
    basicConfig
    0.69
    AndEndTag
    0.63
    __":
    0.61
     الحره
    0.60
    __':
    0.59
    abetes
    0.56
    verifyException
    0.56
    SequentialGroup
    0.55
     nakalista
    0.55
    Activations Density 0.209%

    No Known Activations