© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3963
    Prev
    Next
    INDEX
    Explanations

    they

    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
     دیکھیے
    -0.83
     تضيفلها
    -0.82
     ComVisible
    -0.66
     périph
    -0.66
     pleins
    -0.62
     AssemblyVersion
    -0.61
     consultato
    -0.59
    
    -0.59
     tartalomajánló
    -0.59
    ❮
    -0.58
    POSITIVE LOGITS
     mess
    0.50
     even
    0.49
     ever
    0.48
     start
    0.45
     par
    0.42
     attempt
    0.42
     touch
    0.42
     weit
    0.41
    ever
    0.41
    StructEnd
    0.41
    Activations Density 0.002%

    No Known Activations