© 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. 5-CLT-HP
    7. 92921
    Prev
    Next
    INDEX
    Explanations

    creation

    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
    ChildScrollView
    -0.65
     BoxFit
    -0.57
    ?,?,
    -0.57
    Soap
    -0.52
    cinia
    -0.51
    ngdoc
    -0.49
    责任编辑
    -0.49
     Speech
    -0.49
    TabIndex
    -0.48
     Soap
    -0.48
    POSITIVE LOGITS
    новниш
    0.66
    fromnode
    0.57
    LEADING
    0.55
    govina
    0.54
    DrawerLayout
    0.52
     intptr
    0.52
    Enllaços
    0.52
    acağ
    0.51
    لیس
    0.51
    tonsoft
    0.51
    Activations Density 0.000%

    No Known Activations