© 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. 5-CLT-HP
    7. 91912
    Prev
    Next
    INDEX
    Explanations

    way

    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
    tvguidetime
    -0.79
    >*/
    -0.69
     propOrder
    -0.68
    balleur
    -0.66
    OGND
    -0.65
     GenerationType
    -0.65
    SpringBootTest
    -0.64
     Efq
    -0.63
    tonode
    -0.63
    WSER
    -0.62
    POSITIVE LOGITS
    .
    0.69
    发表于
    0.48
     better
    0.47
    AutoresizingMask
    0.46
    sprogramm
    0.45
    ;
    0.44
    displayquote
    0.44
    løs
    0.43
    styrelsen
    0.43
     of
    0.42
    Activations Density 0.000%

    No Known Activations