© 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. 180
    Prev
    Next
    INDEX
    Explanations

    period

    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
     entanto
    -0.59
     portanto
    -0.59
     purpoſe
    -0.57
    だからこそ
    -0.55
     поэтому
    -0.55
     so
    -0.54
    ẻo
    -0.54
     ſever
    -0.54
    但这
    -0.53
     analiza
    -0.52
    POSITIVE LOGITS
    sidemargin
    0.69
     @"/
    0.65
     it
    0.59
    styleType
    0.59
    /**
    0.57
    AnchorStyles
    0.56
     AppCompat
    0.55
    ngdoc
    0.53
    éndole
    0.52
     <>",
    0.50
    Activations Density 0.036%

    No Known Activations