© 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. 38570
    Prev
    Next
    INDEX
    Explanations

    remaining

    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
     remaining
    -1.49
    remaining
    -1.38
     Remaining
    -1.23
     evolved
    -1.05
    Remaining
    -1.03
     restantes
    -0.98
    ſelves
    -0.86
     workforce
    -0.86
    maining
    -0.82
     evolve
    -0.82
    POSITIVE LOGITS
    不下
    0.45
     fond
    0.44
    x
    0.43
    B
    0.43
    id
    0.43
     very
    0.41
    ev
    0.41
     
    0.41
    1
    0.40
    One
    0.40
    Activations Density 0.018%

    No Known Activations