© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92328
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.78
    verwijspagina
    -0.63
    Vidite
    -0.62
    曖昧さ回避
    -0.60
    Šaltiniai
    -0.59
     Which
    -0.58
     enkelte
    -0.56
     للمعارف
    -0.55
     Another
    -0.54
    jsii
    -0.54
    POSITIVE LOGITS
     might
    0.57
     favorite
    0.54
     can
    0.52
     feels
    0.52
     could
    0.51
     felt
    0.50
     hasn
    0.50
    WebVitals
    0.50
     preferred
    0.48
     background
    0.48
    Activations Density 0.014%

    No Known Activations