© 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. 5-CLT-HP
    7. 92506
    Prev
    Next
    INDEX
    Explanations

    coding and technical writing

    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
    ngrx
    -0.49
    dep
    -0.48
     AP
    -0.48
     Ap
    -0.47
    bq
    -0.47
    vores
    -0.46
    Mounted
    -0.46
     Dep
    -0.45
     Cra
    -0.45
    pat
    -0.45
    POSITIVE LOGITS
     CommonModule
    0.72
    AnimationsModule
    0.69
     coû
    0.69
     TestBed
    0.63
    ImageContext
    0.60
     CURIAM
    0.59
    CommonModule
    0.58
     jsPsych
    0.56
     ContentValues
    0.56
    xFFFFFF
    0.55
    Activations Density 0.000%

    No Known Activations