© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    olol

    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
    metto
    -0.82
    olol
    -0.80
     iprot
    -0.60
     rhestr
    -0.55
     tæt
    -0.52
     justiça
    -0.52
     Montagne
    -0.48
     Replacement
    -0.48
    日閲覧
    -0.47
     roda
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.71
    __':
    0.66
    __':
    0.63
    __":
    0.59
    AsUp
    0.57
    MemoryWarning
    0.57
     дописавши
    0.56
    enol
    0.55
    __":
    0.54
    EClass
    0.52
    Activations Density 0.001%

    No Known Activations