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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2621
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    minar
    -0.46
    liner
    -0.43
    essen
    -0.41
    eles
    -0.41
    plink
    -0.40
    enas
    -0.40
     diret
    -0.39
    ttes
    -0.39
    upt
    -0.39
    esses
    -0.38
    POSITIVE LOGITS
     has
    1.18
     is
    1.01
     ranks
    0.84
     occupies
    0.82
     had
    0.82
     holds
    0.81
     possesses
    0.81
     boasts
    0.81
     adopts
    0.76
     offers
    0.75
    Activations Density 0.005%

    No Known Activations