© 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. 1796
    Prev
    Next
    INDEX
    Explanations

    electronics/engineering

    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
    setVerticalGroup
    -0.81
     plate
    -0.68
    chism
    -0.60
     Arjuna
    -0.59
     Plate
    -0.58
    gdala
    -0.56
     plates
    -0.56
    Plate
    -0.56
    исленность
    -0.56
    plate
    -0.56
    POSITIVE LOGITS
    <bos>
    0.59
    aktery
    0.55
     checksum
    0.50
    VideoCapture
    0.49
    Demografie
    0.49
    tku
    0.48
     geschafft
    0.48
     Fach
    0.47
    odiment
    0.47
    Collegamenti
    0.47
    Activations Density 1.003%

    No Known Activations