© 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. 2780
    Prev
    Next
    INDEX
    Explanations

    and

    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
    tvguidetime
    -0.72
     the
    -0.55
     تضيفلها
    -0.55
    SizeF
    -0.55
     overall
    -0.55
    Datuak
    -0.55
    PhysRev
    -0.52
    GEBURTS
    -0.51
    DateTimeField
    -0.50
    mergeFrom
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.63
     nakalista
    0.52
    '))
    0.51
    ########.
    0.50
    ';
    0.50
    onnay
    0.49
    expansion
    0.49
    ')}}"
    0.49
     mxArray
    0.47
    transformation
    0.47
    Activations Density 0.005%

    No Known Activations