© 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. 20-CLT-HP
    7. 76728
    Prev
    Next
    INDEX
    Explanations

    -ing actions

    np_max-act-logits · 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
    MigrationBuilder
    -0.64
     talking
    -0.57
    be
    -0.57
    tvguidetime
    -0.57
     CreateTagHelper
    -0.56
    ंदीखरीदारी
    -0.56
     Talking
    -0.55
     receiving
    -0.53
    talking
    -0.53
    Talking
    -0.51
    POSITIVE LOGITS
     installing
    1.08
    installing
    0.88
    Installing
    0.87
     including
    0.84
     Installing
    0.83
     equipping
    0.83
     buying
    0.79
    Including
    0.77
     purchasing
    0.77
     Including
    0.77
    Activations Density 0.001%

    No Known Activations