© 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. 4575
    Prev
    Next
    INDEX
    Explanations

    location/clicking themes

    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
    PhysRevLett
    -0.55
    cokinetic
    -0.53
    picasso
    -0.53
    minecraftforge
    -0.52
    hofen
    -0.50
    ereich
    -0.50
    apuram
    -0.50
     decision
    -0.49
     investment
    -0.49
     folder
    -0.48
    POSITIVE LOGITS
     تضيفلها
    0.63
    Erreferentziak
    0.60
    outside
    0.54
     سكانية
    0.52
     brancas
    0.51
    gráfica
    0.50
     المعيارى
    0.50
    FOOTNOTES
    0.49
     tačiau
    0.48
     <=",
    0.48
    Activations Density 0.004%

    No Known Activations