© 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. 91102
    Prev
    Next
    INDEX
    Explanations

    personal writings

    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
     betweenstory
    -0.68
    :✨
    -0.68
    +#+#
    -0.58
     viewDidLoad
    -0.57
    InSection
    -0.54
    SizeMode
    -0.54
     bParam
    -0.54
     vulgaires
    -0.53
    providedIn
    -0.51
     ordinaire
    -0.51
    POSITIVE LOGITS
    DebuggerNonUser
    0.55
    CloseOperation
    0.54
     Back
    0.49
    JES
    0.48
    bootstrapcdn
    0.48
     Chwiliwch
    0.48
    ALLO
    0.47
    Back
    0.46
    End
    0.45
    Портал
    0.45
    Activations Density 0.001%

    No Known Activations