© 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. 94409
    Prev
    Next
    INDEX
    Explanations

    synthetic

    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
     synthetic
    -1.01
    utuhkan
    -0.71
     utafitiHapana
    -0.70
    tonode
    -0.69
     useHistory
    -0.66
     jsPsych
    -0.65
     المعيارى
    -0.65
    synthetic
    -0.63
    ChildScrollView
    -0.63
     MessageBoxIcon
    -0.61
    POSITIVE LOGITS
    ALLY
    0.58
    ally
    0.57
    λογία
    0.53
    tri
    0.52
     intptr
    0.50
    ventus
    0.49
    tra
    0.48
     compagn
    0.48
    dominant
    0.48
    ald
    0.47
    Activations Density 1.053%

    No Known Activations