© 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. 1-CLT-HP
    7. 12462
    Prev
    Next
    INDEX
    Explanations

    Patent

    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
    /**
    -0.67
    migrationBuilder
    -0.65
    protoimpl
    -0.62
     GlobalKey
    -0.61
    //});
    -0.61
     defaultstate
    -0.59
    /−
    -0.58
     Toler
    -0.58
    hyo
    -0.57
    }],
    -0.57
    POSITIVE LOGITS
    AnchorStyles
    0.47
    ftagPool
    0.47
    mot
    0.46
    man
    0.46
     noqa
    0.45
     сно
    0.44
     community
    0.44
    RegistryLite
    0.44
    plish
    0.44
    (
    0.43
    Activations Density 0.010%

    No Known Activations