© 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. 5024
    Prev
    Next
    INDEX
    Explanations

    the

    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
     t
    -0.46
     reason
    -0.46
    tai
    -0.44
     he
    -0.44
     turning
    -0.43
     Rec
    -0.42
     den
    -0.42
     שוליים
    -0.41
    hat
    -0.41
     turned
    -0.40
    POSITIVE LOGITS
     woods
    0.79
    hdashline
    0.73
     esternos
    0.67
    ########.
    0.66
     aveug
    0.65
    ulemon
    0.65
     peindre
    0.63
    bootstrapcdn
    0.63
     slika
    0.62
     küche
    0.61
    Activations Density 0.004%

    No Known Activations