© 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. 0-CLT-HP
    7. 42043
    Prev
    Next
    INDEX
    Explanations

    2

    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
    2
    -0.74
    atu
    -0.50
    com
    -0.49
    UPO
    -0.47
    to
    -0.47
    tip
    -0.47
    sub
    -0.46
    TO
    -0.46
    tof
    -0.44
    RegisterType
    -0.44
    POSITIVE LOGITS
    '},
    1.02
    aarrggbb
    0.96
     Italijanski
    0.90
    ")"
    0.88
    SEGUIR
    0.87
    "},
    0.85
    /−
    0.85
    nd
    0.82
     IBOutlet
    0.82
     bezeichneter
    0.82
    Activations Density 0.798%

    No Known Activations