© 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. 16102
    Prev
    Next
    INDEX
    Explanations

    have

    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
     alike
    -0.61
    webtoken
    -0.55
    careous
    -0.54
     chng
    -0.53
    testcase
    -0.51
     externi
    -0.51
    osoba
    -0.50
    bilirsiniz
    -0.48
    Földrajzportál
    -0.47
    ornment
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.83
    rungsseite
    0.75
    SourceChecksum
    0.73
    Kaynakça
    0.65
    ⓧ
    0.61
     raiſ
    0.59
    ://"
    0.58
     userSchema
    0.57
     ?>/
    0.56
    ConstraintMaker
    0.56
    Activations Density 0.108%

    No Known Activations