© 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. 5792
    Prev
    Next
    INDEX
    Explanations

    to

    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
    
    -0.59
    withIdentifier
    -0.58
    TagMode
    -0.57
     estekak
    -0.54
    featureID
    -0.50
    SharedCtor
    -0.50
    complexContent
    -0.48
     infatti
    -0.48
    batore
    -0.48
    iast
    -0.47
    POSITIVE LOGITS
     reach
    1.16
    reach
    0.89
    Reach
    0.78
     arrive
    0.76
     access
    0.76
     reaches
    0.75
    sistors
    0.68
     Reach
    0.66
    ']))
    0.65
     locations
    0.63
    Activations Density 0.001%

    No Known Activations