© 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. 92205
    Prev
    Next
    INDEX
    Explanations

    birth

    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
    rods
    -0.64
    ctools
    -0.61
     RouterModule
    -0.60
    Життєпис
    -0.59
     متعلقه
    -0.58
    ukone
    -0.58
    StoryboardSegue
    -0.58
     refusé
    -0.58
    handelt
    -0.57
    JsonHelper
    -0.57
    POSITIVE LOGITS
     alive
    0.45
    Personendaten
    0.43
    gameserver
    0.42
    SerializedSize
    0.42
    rawDesc
    0.41
     abroad
    0.40
    insic
    0.38
     latein
    0.38
    elsif
    0.38
     living
    0.36
    Activations Density 0.001%

    No Known Activations