© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1587
    Prev
    Next
    INDEX
    Explanations

    against across

    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
    TypedDataSet
    -0.67
    VideoCapture
    -0.58
     different
    -0.52
    jasama
    -0.52
    ,
    -0.51
     facie
    -0.50
     unspecified
    -0.49
     Pascual
    -0.49
    Décès
    -0.49
    MockBean
    -0.49
    POSITIVE LOGITS
    >--}}
    0.72
    ]-->
    0.63
    extAlignment
    0.61
    )__
    0.59
     متعلقه
    0.58
     utafitiHapana
    0.57
    ."],
    0.55
    AddTagHelper
    0.54
    omeness
    0.54
    ValueGeneration
    0.54
    Activations Density 0.492%

    No Known Activations