© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1038
    Prev
    Next
    INDEX
    Explanations

    bespoke

    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
     Efq
    -0.72
     Monfieur
    -0.72
     يتيمه
    -0.69
     spécialisé
    -0.68
    Specialist
    -0.68
     specializing
    -0.66
    specialist
    -0.66
     passés
    -0.65
     specializes
    -0.63
     Jefus
    -0.63
    POSITIVE LOGITS
    didSet
    0.69
    ed
    0.68
    e
    0.59
    DockStyle
    0.56
     UnityEngine
    0.56
    endphp
    0.55
    mybatisplus
    0.54
    Portail
    0.54
    HasForeignKey
    0.53
    sing
    0.52
    Activations Density 0.033%

    No Known Activations