© 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. 6263
    Prev
    Next
    INDEX
    Explanations

    latitude longitude coordinates

    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
    دانشنامهٔ
    -0.56
    জন
    -0.47
    IntentFilter
    -0.45
    ον
    -0.42
     TextAppearance
    -0.42
    textTheme
    -0.42
    east
    -0.42
    astrar
    -0.41
     places
    -0.41
     sayur
    -0.40
    POSITIVE LOGITS
    TestingModule
    0.63
    LookAnd
    0.60
    WriteAttribute
    0.57
     iprot
    0.56
    SourceChecksum
    0.53
     صوتيه
    0.52
    featureID
    0.51
    oglobulin
    0.50
    NameInMap
    0.50
     שוליים
    0.50
    Activations Density 0.001%

    No Known Activations