© 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. 20-CLT-HP
    7. 74764
    Prev
    Next
    INDEX
    Explanations

    writings

    np_max-act-logits · 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
     InputDecoration
    -0.47
     par
    -0.44
     skut
    -0.43
    anasia
    -0.42
     Effect
    -0.39
     Activity
    -0.39
    PostMapping
    -0.39
    IBOutlet
    -0.39
    Control
    -0.39
    par
    -0.39
    POSITIVE LOGITS
    #+#
    1.06
     propOrder
    0.73
    RegressionTest
    0.70
    +#+
    0.67
     tartalomajánló
    0.66
     language
    0.65
     Langu
    0.64
    zzleHttp
    0.63
     Архів
    0.61
    énario
    0.60
    Activations Density 0.001%

    No Known Activations