© 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. 1-CLT-HP
    7. 14456
    Prev
    Next
    INDEX
    Explanations

    lines

    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
    EndContext
    -0.54
    belum
    -0.51
    ستگی
    -0.50
    BeginContext
    -0.50
     of
    -0.50
    AccessorTable
    -0.48
     Line
    -0.47
     Around
    -0.47
    
    -0.46
    rawdę
    -0.46
    POSITIVE LOGITS
    /*
    0.68
    boutin
    0.68
    ecap
    0.58
     BoxFit
    0.57
    кистан
    0.52
     picioare
    0.52
     Cava
    0.51
     wardrobes
    0.51
    Caprio
    0.51
    Diwedd
    0.49
    Activations Density 0.029%

    No Known Activations