© 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. 4-CLT-HP
    7. 5002
    Prev
    Next
    INDEX
    Explanations

    code/URLs

    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
     break
    -0.44
     us
    -0.42
     modern
    -0.42
     years
    -0.41
    iciones
    -0.41
     all
    -0.41
     var
    -0.40
     you
    -0.39
     some
    -0.39
     they
    -0.38
    POSITIVE LOGITS
     Bioaccumulative
    0.89
    Espèce
    0.86
     otomatig
    0.69
    InjectAttribute
    0.66
     onBind
    0.65
    oa̍t
    0.63
    ChildIndex
    0.61
     defStyle
    0.61
     Италијани
    0.60
    ABUL
    0.60
    Activations Density 0.014%

    No Known Activations