© 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. 15857
    Prev
    Next
    INDEX
    Explanations

    would

    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
    ]")]
    -0.58
    aktery
    -0.57
     fieldNum
    -0.55
     חיצוניים
    -0.55
     FormsModule
    -0.54
    цездатний
    -0.54
    ioa
    -0.52
     setTotal
    -0.52
    ModelAdmin
    -0.51
     defaultstate
    -0.49
    POSITIVE LOGITS
    IVEREF
    0.57
     سكانية
    0.54
     berarti
    0.54
    SourceChecksum
    0.50
    DoubleQuotes
    0.50
     peggio
    0.50
    big
    0.49
    TagHelper
    0.49
     podí
    0.48
    mean
    0.47
    Activations Density 0.008%

    No Known Activations