© 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. 6235
    Prev
    Next
    INDEX
    Explanations

    code

    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
     hyper
    -0.39
     m
    -0.39
     road
    -0.37
    Ђ
    -0.37
     context
    -0.36
     much
    -0.35
     pla
    -0.35
     total
    -0.35
     v
    -0.35
     labor
    -0.35
    POSITIVE LOGITS
    GEBURTSDATUM
    0.87
    contentLoaded
    0.84
    MessageOf
    0.83
    InjectAttribute
    0.83
     Signalez
    0.81
    InitVars
    0.81
    Personendaten
    0.81
     Wikimedijinoj
    0.81
    Personensuche
    0.76
    bewerken
    0.75
    Activations Density 0.001%

    No Known Activations