© 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. 5-CLT-HP
    7. 3147
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
    featureID
    -0.91
    SequentialGroup
    -0.91
    GOTREF
    -0.90
    TagMode
    -0.76
     makeStyles
    -0.76
     MainAxisSize
    -0.75
    MigrationBuilder
    -0.72
    
    -0.72
     tartalomajánló
    -0.70
     noDo
    -0.68
    POSITIVE LOGITS
     from
    0.51
     than
    0.50
     Zimmerman
    0.49
    ruka
    0.47
     mere
    0.47
    annica
    0.46
     Rob
    0.45
     shear
    0.45
     inspection
    0.45
     determination
    0.45
    Activations Density 0.003%

    No Known Activations