© 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. 4-CLT-HP
    7. 1239
    Prev
    Next
    INDEX
    Explanations

    formal documents

    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
     CreateTagHelper
    -0.51
    AccessorTable
    -0.50
    ссора
    -0.48
    stateProvider
    -0.47
    ChildScrollView
    -0.46
    UserScript
    -0.45
    tableFuture
    -0.45
    featureID
    -0.44
    ///</
    -0.44
    OneToMany
    -0.44
    POSITIVE LOGITS
     ſtate
    0.61
     cæ
    0.58
     ftate
    0.52
     themſelves
    0.52
     auffi
    0.51
     myſelf
    0.50
     beſt
    0.50
     ſte
    0.50
     category
    0.49
    InputBorder
    0.49
    Activations Density 0.041%

    No Known Activations