© 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. 650
    Prev
    Next
    INDEX
    Explanations

    conjunctions, prepositions

    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
    +#+#
    -0.56
     forKey
    -0.56
     TestBed
    -0.54
     aDecoder
    -0.51
     himo
    -0.50
    respectively
    -0.50
     المرجع
    -0.50
    forKey
    -0.50
    ToBounds
    -0.49
    xase
    -0.49
    POSITIVE LOGITS
    <bos>
    1.32
     enfans
    0.60
    /*
    0.59
     ſta
    0.59
    RegistryLite
    0.59
     this
    0.59
     whoſe
    0.56
     preſ
    0.56
     ſtre
    0.56
     ſay
    0.54
    Activations Density 0.010%

    No Known Activations