© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 4841
    Prev
    Next
    INDEX
    Explanations

    to

    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
    StoryboardSegue
    -0.57
    Jeografia
    -0.54
    rule
    -0.52
    SharedCtor
    -0.51
     NSCoder
    -0.51
    store
    -0.49
    łoń
    -0.47
     endwhile
    -0.47
     كومونز
    -0.46
    IMON
    -0.46
    POSITIVE LOGITS
    ymce
    0.56
    mybatisplus
    0.52
     OnInit
    0.51
    WebServlet
    0.51
     vectors
    0.49
     Prev
    0.49
    transQ
    0.48
    MIDDLEWARE
    0.48
    /**
    0.46
    diger
    0.46
    Activations Density 0.004%

    No Known Activations