© 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. 4345
    Prev
    Next
    INDEX
    Explanations

    hazel

    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
     jScrollPane
    -0.68
    +#+
    -0.56
     okuyayım
    -0.54
    beforeEach
    -0.52
    VideoCapture
    -0.50
    paq
    -0.49
     aimer
    -0.47
    UnusedPrivate
    -0.47
    GZIP
    -0.46
    minecraftforge
    -0.46
    POSITIVE LOGITS
    nuts
    0.69
     grouse
    0.60
    nows
    0.58
    nue
    0.56
    nu
    0.56
    noinspection
    0.55
    reht
    0.55
    enas
    0.54
    neth
    0.53
    nus
    0.52
    Activations Density 0.001%

    No Known Activations