© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92230
    Prev
    Next
    INDEX
    Explanations

    tere

    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
    fton
    -1.77
    ODY
    -0.56
    zzly
    -0.54
     AssemblyTitle
    -0.48
    rungsseite
    -0.47
    findpost
    -0.47
    waitKey
    -0.46
    UIApplication
    -0.45
    ship
    -0.45
    ExecuteReader
    -0.45
    POSITIVE LOGITS
    ngths
    0.69
     betweenstory
    0.62
    getMenuInflater
    0.60
    writeFieldEnd
    0.59
    StoryboardSegue
    0.58
    CodeAttribute
    0.57
    SequentialGroup
    0.57
    HomeAsUpEnabled
    0.56
     nostrils
    0.56
     ifrån
    0.56
    Activations Density 0.021%

    No Known Activations