© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93003
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ⓧ
    -0.80
    UnusedPrivate
    -0.76
    genicity
    -0.60
    NamedQueries
    -0.60
     inducement
    -0.59
     Exacts
    -0.59
     BrowserModule
    -0.57
     sorgen
    -0.57
    artifactId
    -0.56
    DotNetBar
    -0.54
    POSITIVE LOGITS
     someday
    0.55
     want
    0.54
     grow
    0.54
     eventually
    0.54
     like
    0.54
     be
    0.49
     grew
    0.49
     love
    0.49
     виправивши
    0.48
     have
    0.47
    Activations Density 0.001%

    No Known Activations