© 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. 0-CLT-HP
    7. 41977
    Prev
    Next
    INDEX
    Explanations

    document boundaries

    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
     BrowserModule
    -0.72
     Administrativna
    -0.66
     الحره
    -0.65
     The
    -0.57
     ErrIntOverflow
    -0.56
    ResumeLayout
    -0.52
    piram
    -0.52
     tuyến
    -0.51
    ẾT
    -0.51
    velmente
    -0.51
    POSITIVE LOGITS
    mulher
    0.57
    zman
    0.52
     getItemId
    0.51
    awtextra
    0.50
    XDECREF
    0.50
    CURLOPT
    0.50
    AnchorStyles
    0.50
     abſ
    0.49
    Biographie
    0.49
    ]=='
    0.49
    Activations Density 1.398%

    No Known Activations