© 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. 1-CLT-HP
    7. 928
    Prev
    Next
    INDEX
    Explanations

    rshire

    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
    vo
    -0.73
    Vo
    -0.61
    VO
    -0.60
     vo
    -0.56
    vola
    -0.56
    vos
    -0.48
     Vo
    -0.48
    ia
    -0.48
     Fow
    -0.48
     Fou
    -0.47
    POSITIVE LOGITS
     Precis
    0.73
     AssemblyCompany
    0.69
    horabuena
    0.66
    ynchronously
    0.66
    micamente
    0.66
    AndEndTag
    0.63
     MainAxisSize
    0.61
    DockStyle
    0.60
     محفوظة
    0.59
     PhpStorm
    0.58
    Activations Density 0.012%

    No Known Activations