© 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. 5-CLT-HP
    7. 93679
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
    IVEREF
    -0.71
     puissiez
    -0.58
     Roskov
    -0.57
     Réponses
    -0.57
    seamnă
    -0.54
    XmlAccessType
    -0.54
    ChildIndex
    -0.51
    Msk
    -0.50
    󠁴
    -0.50
    COMMERCIAL
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.62
    adaptiveStyles
    0.59
    djangoproject
    0.57
     IDisposable
    0.55
    XmlAccessorType
    0.54
    __":
    0.53
    TagHelpers
    0.52
    PropertyChanging
    0.51
    enschutz
    0.50
     poveznice
    0.48
    Activations Density 0.232%

    No Known Activations