© 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. 5-CLT-HP
    7. 96855
    Prev
    Next
    INDEX
    Explanations

    in

    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
     anything
    -0.67
     aught
    -0.63
     Anything
    -0.60
    Anything
    -0.59
    Nothing
    -0.57
    anything
    -0.57
     Nothing
    -0.53
    悪く
    -0.53
    nothing
    -0.52
     ANYTHING
    -0.51
    POSITIVE LOGITS
    adpleegd
    0.79
     Wikimedijinoj
    0.78
    XmlAccessType
    0.75
    mybatisplus
    0.74
    #
    0.71
    AccessorTable
    0.69
    featureID
    0.68
    RegistryLite
    0.68
    Personendaten
    0.65
    JNIEnv
    0.64
    Activations Density 0.002%

    No Known Activations