© 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. 90815
    Prev
    Next
    INDEX
    Explanations

    ceptors

    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
     Efq
    -1.21
     pleaſure
    -1.03
     Theſe
    -1.00
    ^(@)
    -0.97
     myſelf
    -0.96
     ſeveral
    -0.94
     Jefus
    -0.94
     Monfieur
    -0.94
     Majefty
    -0.93
    ſelves
    -0.91
    POSITIVE LOGITS
    ult
    0.56
    ing
    0.54
    P
    0.53
     P
    0.52
     Mar
    0.51
    V
    0.51
    on
    0.50
     Al
    0.50
    or
    0.50
     Ra
    0.49
    Activations Density 0.066%

    No Known Activations