© 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. 4-CLT-HP
    7. 575
    Prev
    Next
    INDEX
    Explanations

    set

    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
    WireFormatLite
    -0.73
     myſelf
    -0.66
     doubtnut
    -0.63
    )");
    -0.59
     ſch
    -0.57
    WriteBarrier
    -0.56
     muri
    -0.55
    ])));
    -0.55
     photographers
    -0.55
     pixels
    -0.55
    POSITIVE LOGITS
     Law
    0.53
     Plan
    0.52
     No
    0.51
     Record
    0.50
     Test
    0.50
     Control
    0.49
     Design
    0.49
     Ad
    0.49
     سكانية
    0.48
     Me
    0.47
    Activations Density 0.001%

    No Known Activations