© 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. 93058
    Prev
    Next
    INDEX
    Explanations

    Research papers

    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
    Personensuche
    -0.92
    sizeCache
    -0.91
     Administrativna
    -0.89
    AddTagHelper
    -0.83
     ostavi
    -0.76
     evolve
    -0.75
     Réponses
    -0.75
    evolve
    -0.74
     estekak
    -0.74
    Geplaatst
    -0.73
    POSITIVE LOGITS
    zai
    0.48
     Encoding
    0.46
    lata
    0.46
    defn
    0.45
    hauser
    0.44
    Encoding
    0.43
     Arque
    0.42
    ไร
    0.41
     flex
    0.40
    Gön
    0.40
    Activations Density 0.001%

    No Known Activations