© 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. 1-CLT-HP
    7. 15256
    Prev
    Next
    INDEX
    Explanations

    scientific/medical articles

    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
    artifactId
    -0.58
     finger
    -0.57
    raw
    -0.54
    Salty
    -0.48
    Finger
    -0.48
    newArrayList
    -0.48
    ogaster
    -0.47
    aic
    -0.47
    Geografie
    -0.45
    Jeografia
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.87
    FieldBuilder
    0.77
    SourceChecksum
    0.68
    tagHelperRunner
    0.67
     beginnetje
    0.65
    ScopeManager
    0.60
    bootstrapcdn
    0.60
     otomatig
    0.59
     GenerationType
    0.59
    ResumeLayout
    0.59
    Activations Density 0.040%

    No Known Activations