© 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. 0-CLT-HP
    7. 90472
    Prev
    Next
    INDEX
    Explanations

    correct

    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
     correct
    -1.77
    correct
    -1.74
    Correct
    -1.51
     accurate
    -1.36
     Correct
    -1.34
     correctly
    -1.30
     CORRECT
    -1.17
     therefore
    -1.14
     correcte
    -1.13
     correcto
    -1.10
    POSITIVE LOGITS
    Portale
    0.71
    lapsingToolbar
    0.65
    ingway
    0.65
    CloseOperation
    0.63
    osoba
    0.60
    issors
    0.59
    Портал
    0.57
    ibouti
    0.57
    ỡng
    0.56
     Pah
    0.56
    Activations Density 1.915%

    No Known Activations