© 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. 5-CLT-HP
    7. 92711
    Prev
    Next
    INDEX
    Explanations

    of

    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
    OGND
    -0.89
    StructEnd
    -0.85
    tagext
    -0.73
     CreateTagHelper
    -0.72
    IntoConstraints
    -0.70
    Portale
    -0.66
    期刊论文
    -0.65
     Administrativna
    -0.65
    Personensuche
    -0.65
     wireType
    -0.65
    POSITIVE LOGITS
    /**
    0.61
    /*
    0.54
    //
    0.53
     considering
    0.52
    #
    0.48
     evaluating
    0.44
     employing
    0.44
     properly
    0.44
    <eos>
    0.42
     using
    0.41
    Activations Density 0.004%

    No Known Activations