© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3593
    Prev
    Next
    INDEX
    Explanations

    this

    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
     esternos
    -0.55
    EndContext
    -0.52
     متعلقه
    -0.48
     utafitiHapana
    -0.47
     preghi
    -0.46
    mær
    -0.45
     you
    -0.44
    mbalikan
    -0.44
     riguard
    -0.42
    fhir
    -0.42
    POSITIVE LOGITS
    CloseOperation
    0.71
     timely
    0.59
     week
    0.59
    المشاركات
    0.55
     MotionEvent
    0.55
     month
    0.54
     article
    0.54
    DrawerToggle
    0.54
     Alamofire
    0.54
     topic
    0.53
    Activations Density 0.001%

    No Known Activations