© 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. 93432
    Prev
    Next
    INDEX
    Explanations

    relevance

    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
    KommentareTeilen
    -0.54
     GetEnumerator
    -0.50
    addContainerGap
    -0.42
     SearchView
    -0.42
    acją
    -0.42
    Javadoc
    -0.41
    IsMutable
    -0.41
     kaynağından
    -0.41
    vieto
    -0.41
     somewhat
    -0.40
    POSITIVE LOGITS
     agencies
    1.09
     ministers
    1.08
     authorities
    1.08
     ministries
    1.06
     departments
    1.00
     Ministers
    0.99
     stakeholders
    0.96
     organisations
    0.94
     Ministries
    0.94
     institutions
    0.93
    Activations Density 0.001%

    No Known Activations