© 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. 92015
    Prev
    Next
    INDEX
    Explanations

    Eating

    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
    skosten
    -0.65
    GEBURTSDATUM
    -0.63
    Portale
    -0.59
     useStyles
    -0.57
    Carriera
    -0.56
    ponses
    -0.56
     esternos
    -0.55
    ]),
    -0.55
    Tikang
    -0.54
     initState
    -0.54
    POSITIVE LOGITS
     group
    0.89
    group
    0.79
     stuff
    0.72
    stuff
    0.71
     Group
    0.63
     Stuff
    0.63
    Stuff
    0.62
     grupo
    0.61
     GROUP
    0.60
     item
    0.58
    Activations Density 0.000%

    No Known Activations