© 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. 93373
    Prev
    Next
    INDEX
    Explanations

    was

    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
    tgz
    -0.50
     PhpStorm
    -0.46
    oplayer
    -0.46
    thenReturn
    -0.46
    StoreMessageInfo
    -0.45
    getMenuInflater
    -0.45
    HostException
    -0.44
     springfox
    -0.44
    Distribución
    -0.44
    angsaan
    -0.44
    POSITIVE LOGITS
     surla
    0.68
     inspired
    0.62
    PYX
    0.57
     objectifs
    0.53
     nhật
    0.51
     aided
    0.50
     aidé
    0.50
    Rhestr
    0.50
    iliar
    0.50
    Collabor
    0.49
    Activations Density 0.006%

    No Known Activations