© 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. 5-CLT-HP
    7. 96945
    Prev
    Next
    INDEX
    Explanations

    in

    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
    <bos>
    -0.57
    श्व
    -0.56
    antry
    -0.53
    omitempty
    -0.52
    %")
    -0.51
    )
    -0.50
    urement
    -0.49
    ftagPool
    -0.49
     tuyển
    -0.48
    彼が
    -0.48
    POSITIVE LOGITS
     sumpay
    0.65
     people
    0.54
     Waray
    0.52
    rawDesc
    0.50
    цтва
    0.49
    InitStruct
    0.47
    prefixer
    0.47
    arraycopy
    0.47
    Referanser
    0.47
    deelte
    0.46
    Activations Density 0.005%

    No Known Activations