© 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. 0-CLT-HP
    7. 41943
    Prev
    Next
    INDEX
    Explanations

    consider

    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
     considered
    -1.61
     consider
    -1.47
    considered
    -1.39
     considering
    -1.36
     CONSIDER
    -1.36
     considers
    -1.26
     Considered
    -1.25
     considerato
    -1.23
    considering
    -1.22
     considerar
    -1.19
    POSITIVE LOGITS
    ſelf
    0.89
     ſmall
    0.89
     Monfieur
    0.89
     Majefty
    0.88
     Diſ
    0.87
     ſche
    0.86
     ſtate
    0.85
     iſt
    0.83
     Eſ
    0.83
     pleaſure
    0.82
    Activations Density 0.166%

    No Known Activations