© 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. 845
    Prev
    Next
    INDEX
    Explanations

    changing states

    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
     unknownFields
    -0.59
    awtextra
    -0.59
    BarStyle
    -0.58
     Оно
    -0.56
    XtraEditors
    -0.55
    potranspiration
    -0.54
     emperors
    -0.53
     }}^{
    -0.52
    ]")]
    -0.52
    曖昧さ回避
    -0.51
    POSITIVE LOGITS
     your
    0.82
     yourself
    0.79
     oneself
    0.66
     something
    0.64
     hands
    0.57
     an
    0.57
     a
    0.53
    Yourself
    0.52
     the
    0.52
     myself
    0.52
    Activations Density 0.002%

    No Known Activations