© 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. 4-CLT-HP
    7. 203
    Prev
    Next
    INDEX
    Explanations

    :

    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
    reactstrap
    -0.65
    sizeCache
    -0.59
     AssemblyCompany
    -0.59
    makeConstraints
    -0.58
    templateUrl
    -0.58
    دانشنامهٔ
    -0.55
    NgModule
    -0.55
    featureID
    -0.53
    ChildScrollView
    -0.50
    Autoritní
    -0.49
    POSITIVE LOGITS
     chré
    0.78
     commerciaux
    0.67
    PreferredItem
    0.67
     sauvages
    0.66
    0
    0.66
     passés
    0.64
     produisent
    0.63
     achtergrond
    0.63
     juridiques
    0.63
     profondeur
    0.63
    Activations Density 0.010%

    No Known Activations