© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75476
    Prev
    Next
    INDEX
    Explanations

    documents

    np_max-act-logits · 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
    htë
    -0.65
    NegativeButton
    -0.60
     FA
    -0.57
    FA
    -0.56
    <bos>
    -0.50
    have
    -0.50
     Fa
    -0.50
    Persistent
    -0.50
     Faul
    -0.50
    Fa
    -0.49
    POSITIVE LOGITS
     للمعارف
    0.75
    findpost
    0.66
     خارجية
    0.61
     يتيمه
    0.61
     Wiktionnaire
    0.60
    stateProvider
    0.58
     مشين
    0.57
     فريبيس
    0.56
     Normdatei
    0.56
    ThroughAttribute
    0.53
    Activations Density 0.000%

    No Known Activations