© 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. 1-CLT-HP
    7. 15519
    Prev
    Next
    INDEX
    Explanations

    said

    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
    DockStyle
    -0.72
    SequentialGroup
    -0.71
     that
    -0.70
     GenerationType
    -0.64
     they
    -0.63
    IsPostBack
    -0.63
     stating
    -0.58
     saying
    -0.57
    ]")]
    -0.57
    BuildContext
    -0.56
    POSITIVE LOGITS
    yourself
    0.59
     يتيمه
    0.58
    Yourself
    0.57
    situ
    0.56
    rolid
    0.51
     AspNetCore
    0.50
    leet
    0.49
     ourselves
    0.47
    commod
    0.47
     Yourself
    0.47
    Activations Density 0.054%

    No Known Activations