© 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. 0-CLT-HP
    7. 95667
    Prev
    Next
    INDEX
    Explanations

    Possibility/permission

    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
     ‘
    -0.58
    <eos>
    -0.54
     a
    -0.52
     an
    -0.51
    ParallelGroup
    -0.51
     the
    -0.49
     ter
    -0.49
     for
    -0.46
    Παραπομπές
    -0.46
     to
    -0.45
    POSITIVE LOGITS
    URLException
    0.73
     photolibrary
    0.72
    المناصب
    0.69
     Plenum
    0.69
    nologue
    0.68
    yntaxException
    0.68
     ―――――
    0.68
    Datuak
    0.66
     bershka
    0.66
    HostException
    0.66
    Activations Density 0.065%

    No Known Activations