© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    academia, research

    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
    RegressionTest
    -0.49
     setId
    -0.47
    enschap
    -0.46
    ]')
    -0.46
    unj
    -0.46
    urten
    -0.46
    LVANIA
    -0.46
    rds
    -0.46
    찍
    -0.45
    texttt
    -0.45
    POSITIVE LOGITS
     doInBackground
    0.76
    脚注の使い方
    0.70
    OGND
    0.68
     autorytatywna
    0.67
    twimg
    0.65
     ExecuteAsync
    0.60
    AndEndTag
    0.58
     Leopoldo
    0.58
    tvguidetime
    0.57
     ISNI
    0.56
    Activations Density 0.004%

    No Known Activations