© 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. 0-CLT-HP
    7. 43176
    Prev
    Next
    INDEX
    Explanations

    anth

    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
     denied
    -0.90
     ModelExpression
    -0.87
     contained
    -0.85
    contained
    -0.85
    sizeCache
    -0.84
     admitted
    -0.83
    elemField
    -0.83
     mg
    -0.82
     kaarangay
    -0.82
    UnsafeEnabled
    -0.81
    POSITIVE LOGITS
    izm
    0.46
    itys
    0.43
    OfYear
    0.42
    izde
    0.41
    ism
    0.40
     raiſ
    0.40
    ists
    0.39
    initWithFrame
    0.39
    orphism
    0.38
     vielmehr
    0.37
    Activations Density 0.098%

    No Known Activations