© 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. 20-CLT-HP
    7. 75836
    Prev
    Next
    INDEX
    Explanations

    tuned

    np_max-act-logits · 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
     moving
    -1.02
    moving
    -0.97
     Moving
    -0.94
     going
    -0.93
     proceeding
    -0.92
    Moving
    -0.91
     Going
    -0.87
     progressing
    -0.86
    Going
    -0.86
     MOVING
    -0.81
    POSITIVE LOGITS
     مشين
    0.56
    principalColumn
    0.54
     autorytatywna
    0.52
    MemoryWarning
    0.50
     bete
    0.49
    URLException
    0.48
    webElementGuid
    0.46
    afficheront
    0.44
     незавершена
    0.42
     initComponents
    0.41
    Activations Density 0.001%

    No Known Activations