© 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. 41469
    Prev
    Next
    INDEX
    Explanations

    code parsing/debugging

    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
     saites
    -0.94
     ControllerBase
    -0.72
     BoxFit
    -0.67
     Disciples
    -0.66
    LLocation
    -0.65
     noise
    -0.65
    JoinTable
    -0.65
     numberOfRows
    -0.63
    +#+#
    -0.63
    tagez
    -0.62
    POSITIVE LOGITS
    ंदीखरीदारी
    0.64
    e
    0.60
    er
    0.56
    y
    0.55
    ezy
    0.49
     Form
    0.47
    en
    0.46
    fontein
    0.45
    MathML
    0.43
    SequentialGroup
    0.42
    Activations Density 0.130%

    No Known Activations