© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91021
    Prev
    Next
    INDEX
    Explanations

    Phone

    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
    Negative Logits
     tartalomajánló
    -0.47
    ibol
    -0.47
    cinct
    -0.44
    ematic
    -0.44
     ministers
    -0.43
    ‌ش
    -0.43
    TRIBUN
    -0.42
    ensky
    -0.42
    ctable
    -0.42
    psies
    -0.41
    POSITIVE LOGITS
     AssemblyCompany
    0.81
    styleable
    0.69
    PreExecute
    0.66
     GetEnumerator
    0.65
     "..\..\..\
    0.64
     "..\..\
    0.63
    UnsafeEnabled
    0.62
     yyr
    0.62
    ThroughAttribute
    0.61
     defaultstate
    0.59
    Activations Density 0.014%

    No Known Activations