© 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. 1-CLT-HP
    7. 9436
    Prev
    Next
    INDEX
    Explanations

    MOSFETS

    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
    -0.56
    findpost
    -0.55
    脚注の使い方
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    ]--;
    -0.52
    rxjs
    -0.50
    vé
    -0.49
     referenties
    -0.49
    ]++;
    -0.49
    envol
    -0.48
    POSITIVE LOGITS
    XmlAccessType
    0.67
     فريبيس
    0.55
    sidemargin
    0.54
    ">//
    0.51
    (!__
    0.49
    UVWXYZ
    0.49
    LabelTagHelper
    0.49
    InitStruct
    0.49
     electrostatic
    0.47
    ơm
    0.47
    Activations Density 0.093%

    No Known Activations