© 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. 20-CLT-HP
    7. 75757
    Prev
    Next
    INDEX
    Explanations

    identifiers names technical

    np_max-act-logits · 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
    PhysRevD
    -0.53
    uage
    -0.48
     Lightboxes
    -0.48
     quenched
    -0.47
    TestingModule
    -0.47
    Искәрмәләр
    -0.47
    ional
    -0.46
    equila
    -0.46
     useAppContext
    -0.46
    righted
    -0.45
    POSITIVE LOGITS
    NameInMap
    0.65
    ("")]
    0.62
    featureID
    0.59
    AnchorStyles
    0.58
    UrlResolution
    0.55
    IContainer
    0.55
    Personendaten
    0.53
    #+#
    0.50
    Cur
    0.50
     cur
    0.49
    Activations Density 0.000%

    No Known Activations