© 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. 723
    Prev
    Next
    INDEX
    Explanations

    something amiss

    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
     wonders
    -0.44
    ついで
    -0.44
     dials
    -0.43
    endgroup
    -0.43
    стоин
    -0.42
     warrants
    -0.42
    wants
    -0.42
     betweenstory
    -0.42
    pruchs
    -0.42
     hoops
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.69
    Manbalar
    0.57
    \{\\
    0.57
     @"/
    0.57
    出版年
    0.56
    SuppressMessage
    0.56
    LEncoder
    0.55
    limus
    0.54
    CppMethod
    0.53
     brewing
    0.52
    Activations Density 0.005%

    No Known Activations