© 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. 6253
    Prev
    Next
    INDEX
    Explanations

    rivers

    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
     Nature
    -0.65
    Nature
    -0.65
     nature
    -0.60
     natural
    -0.58
    natural
    -0.55
    nature
    -0.54
     NATURE
    -0.53
    joda
    -0.52
     Natur
    -0.50
    Natural
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.98
     ProtoMessage
    0.90
    MigrationBuilder
    0.74
     StatefulWidget
    0.72
    protoimpl
    0.70
     CanadaChoose
    0.69
    Alike
    0.68
    DotNetBar
    0.67
     Exactos
    0.66
    Демографія
    0.65
    Activations Density 0.000%

    No Known Activations