© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 514
    Prev
    Next
    INDEX
    Explanations

    code, licenses, legal decisions

    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
     متعلقه
    -0.82
    CrossRef
    -0.57
    __":
    -0.55
    /**
    -0.53
     noDo
    -0.52
    MemoryWarning
    -0.51
     MonoBehaviour
    -0.51
    LayoutStyle
    -0.49
    UrlResolution
    -0.48
    InvalidProtocol
    -0.48
    POSITIVE LOGITS
     noises
    0.58
    InlineData
    0.56
     signs
    0.56
     tone
    0.55
     signal
    0.55
     juridiques
    0.54
     conclusion
    0.54
     écrits
    0.53
     sinais
    0.53
     headline
    0.52
    Activations Density 0.013%

    No Known Activations