© 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. 4-CLT-HP
    4. 2527
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    떤
    -0.40
    لیسی
    -0.40
     rekke
    -0.40
     âgées
    -0.38
     try
    -0.38
    sal
    -0.38
     Knud
    -0.38
    istö
    -0.37
    ūn
    -0.37
     Willow
    -0.37
    POSITIVE LOGITS
    providedIn
    0.69
     дописавши
    0.67
    expandindo
    0.66
     disambiguazione
    0.65
    nefs
    0.61
    ]--;
    0.60
    wiſe
    0.59
    ableness
    0.58
    CardBody
    0.58
    CTIONS
    0.57
    Activations Density 0.005%

    No Known Activations