© 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. 1-CLT-HP
    7. 15925
    Prev
    Next
    INDEX
    Explanations

    metals

    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
     GST
    -0.65
    elemField
    -0.61
     fieldNum
    -0.54
     BorderSide
    -0.53
    getDoctrine
    -0.52
    gst
    -0.52
    ContextCompat
    -0.52
     AdapterView
    -0.51
    солю
    -0.51
    Strand
    -0.50
    POSITIVE LOGITS
     يتيمه
    0.65
    ="@+
    0.63
    évaluateur
    0.60
    \{\\
    0.59
    KURZBESCHREIBUNG
    0.56
    Rhestr
    0.54
    ViewFeatures
    0.53
    GeneratedCode
    0.53
     gawas
    0.51
     naso
    0.51
    Activations Density 0.043%

    No Known Activations