© 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. 5882
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    twimg
    -0.59
     مشين
    -0.51
    expédition
    -0.51
    opend
    -0.51
    dett
    -0.50
     discovery
    -0.50
    lossus
    -0.50
     discover
    -0.50
    peration
    -0.50
    woordig
    -0.49
    POSITIVE LOGITS
     AttributeSet
    0.65
     "..\..\..\
    0.64
     vPvB
    0.60
    Personendaten
    0.60
     XCTest
    0.59
    DebuggerNonUser
    0.53
    leading
    0.53
    LEADING
    0.53
     "..\..\
    0.49
    TargetApi
    0.49
    Activations Density 0.003%

    No Known Activations