© 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. 96353
    Prev
    Next
    INDEX
    Explanations

    pronounced

    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
     sondern
    -0.84
     anymore
    -0.83
     yet
    -0.83
     but
    -0.77
     melainkan
    -0.77
    fjspx
    -0.76
     tetapi
    -0.71
    rungsseite
    -0.71
     BUT
    -0.71
     Yet
    -0.69
    POSITIVE LOGITS
    ainville
    0.44
    was
    0.44
     environmental
    0.43
    </thead>
    0.43
     climatic
    0.43
     pathways
    0.43
    anging
    0.43
    izing
    0.42
    Cursors
    0.42
     or
    0.41
    Activations Density 0.007%

    No Known Activations