© 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. 77088
    Prev
    Next
    INDEX
    Explanations

    from

    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
     snippetHide
    -0.68
    SpringBoot
    -0.65
    NgModule
    -0.62
     picioare
    -0.56
    etCode
    -0.56
    EXTERN
    -0.56
     stället
    -0.52
     forState
    -0.51
     sesso
    -0.50
    glEnd
    -0.50
    POSITIVE LOGITS
     filters
    0.53
     InputDecoration
    0.53
     adjournment
    0.52
     brakes
    0.52
    AsUp
    0.51
     adjourn
    0.51
     euth
    0.49
     pompe
    0.49
     bep
    0.49
     birthdays
    0.48
    Activations Density 0.000%

    No Known Activations