© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4925
    Prev
    Next
    INDEX
    Explanations

    fractions or portions

    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
     EconPapers
    -0.82
     ExecuteAsync
    -0.77
    MessageOf
    -0.65
    BASEPATH
    -0.64
     oprot
    -0.59
    jamientos
    -0.56
    IsContent
    -0.55
    Personensuche
    -0.54
    djangoproject
    -0.54
    ạch
    -0.53
    POSITIVE LOGITS
    GLOBALS
    0.51
    ::_('
    0.49
    andReturn
    0.47
    回戦
    0.47
    gelijk
    0.46
     transfieras
    0.46
    moveToFirst
    0.45
    љ
    0.45
    .
    0.44
    ocarp
    0.43
    Activations Density 0.002%

    No Known Activations