© 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. 97391
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
     which
    -1.70
    which
    -1.63
    Which
    -1.37
     Which
    -1.27
     WHICH
    -1.24
     mely
    -0.95
     wich
    -0.80
     vilket
    -0.80
     które
    -0.74
    hich
    -0.74
    POSITIVE LOGITS
     works
    0.69
    SBATCH
    0.65
     was
    0.61
     relies
    0.61
     has
    0.59
     guides
    0.58
     فريبيس
    0.57
    Demografia
    0.57
    verläs
    0.57
     leads
    0.56
    Activations Density 0.036%

    No Known Activations