© 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. 97268
    Prev
    Next
    INDEX
    Explanations

    be

    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
     kasarigan
    -0.65
    bootstrapcdn
    -0.57
    rogens
    -0.56
    yntaxException
    -0.54
     {?>
    -0.54
    AnchorStyles
    -0.53
    }:${
    -0.53
    +:+
    -0.53
    ustering
    -0.52
    ignal
    -0.52
    POSITIVE LOGITS
     underestimated
    0.82
     confused
    0.68
     tam
    0.67
     препратки
    0.65
     compared
    0.65
     equated
    0.63
     saites
    0.60
     allowed
    0.59
     mistaken
    0.56
     left
    0.54
    Activations Density 0.003%

    No Known Activations