© 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. 97319
    Prev
    Next
    INDEX
    Explanations

    Moss

    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
    o
    -0.84
    y
    -0.81
    e
    -0.78
    ی
    -0.71
    ه
    -0.66
    ed
    -0.64
    i
    -0.63
    ised
    -0.56
    u
    -0.56
    en
    -0.55
    POSITIVE LOGITS
     itſelf
    1.36
     myſelf
    1.23
     himſelf
    1.20
     themſelves
    1.14
     Majefty
    1.14
     whoſe
    1.13
     Efq
    1.12
    ſelves
    1.11
     purpoſe
    1.09
     becauſe
    1.06
    Activations Density 0.151%

    No Known Activations