© 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. 71542
    Prev
    Next
    INDEX
    Explanations

    Incomplete sentences, uncommon words

    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
    Negative Logits
    LookAnd
    -0.78
    ########.
    -0.67
     StringTokenizer
    -0.62
    
    -0.62
    Pozri
    -0.59
     Dram
    -0.59
    ")));
    -0.57
    DoubleQuotes
    -0.56
    lossians
    -0.56
    (!__
    -0.56
    POSITIVE LOGITS
     nakalista
    0.47
    mybatisplus
    0.46
    esgue
    0.44
     noDo
    0.44
    stretchr
    0.43
    reme
    0.43
    UnsafeEnabled
    0.40
    fjspx
    0.38
    ValueGeneration
    0.38
     der
    0.37
    Activations Density 0.000%

    No Known Activations