© 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. 3304
    Prev
    Next
    INDEX
    Explanations

    Companies

    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>
    -0.52
    ########.
    -0.50
    InitStruct
    -0.48
    AndEndTag
    -0.48
    ene
    -0.47
    AddHtmlAttribute
    -0.46
     صوتيه
    -0.44
    onAttach
    -0.43
     ivelany
    -0.43
    ToTensor
    -0.42
    POSITIVE LOGITS
     CEO
    0.68
     ceo
    0.65
     unveiled
    0.64
     CFO
    0.61
     planea
    0.60
     anunció
    0.60
     executives
    0.60
     annonce
    0.59
    ALOG
    0.59
    agascar
    0.59
    Activations Density 0.005%

    No Known Activations