© 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. 94395
    Prev
    Next
    INDEX
    Explanations

    disasters

    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
    MessageOf
    -0.82
    featureID
    -0.77
    tonode
    -0.66
     disambiguazione
    -0.65
    OrNil
    -0.64
    Parcelize
    -0.64
     putea
    -0.63
     propOrder
    -0.62
     RIPRODUZIONE
    -0.60
    InitVars
    -0.60
    POSITIVE LOGITS
     declines
    0.49
    ietf
    0.44
    AddHtmlAttribute
    0.42
    ই
    0.40
    bParam
    0.40
     teritor
    0.40
     inc
    0.38
     concern
    0.38
     emot
    0.37
     rec
    0.37
    Activations Density 0.004%

    No Known Activations