© 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. 0-CLT-HP
    7. 2005
    Prev
    Next
    INDEX
    Explanations

    ically

    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
    ically
    -1.04
    atically
    -1.00
    sense
    -0.90
    Sense
    -0.88
     sense
    -0.86
    hetically
    -0.77
    
    -0.74
    
    -0.73
     Sense
    -0.70
    enses
    -0.64
    POSITIVE LOGITS
    хьтан
    0.57
    <bos>
    0.46
    ,
    0.43
    WireFormat
    0.41
    confirm
    0.41
    ρός
    0.40
    bbene
    0.40
    fäl
    0.40
    doria
    0.40
     {:.
    0.40
    Activations Density 0.151%

    No Known Activations