© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71647
    Prev
    Next
    INDEX
    Explanations

    formal language

    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
    Tikang
    -0.96
     ExecuteAsync
    -0.81
    extAlignment
    -0.68
     getRule
    -0.63
     AppComponent
    -0.61
    richTextPanel
    -0.61
    rungsseite
    -0.59
     Baillargeon
    -0.59
    tallet
    -0.58
    esModule
    -0.58
    POSITIVE LOGITS
    sparse
    0.43
     inter
    0.43
     British
    0.39
    inter
    0.39
    ▬
    0.38
     SD
    0.38
    HashCode
    0.37
    FormBuilder
    0.37
    dafrika
    0.36
     third
    0.36
    Activations Density 0.002%

    No Known Activations