© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93877
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ⓧ
    -0.52
    enderror
    -0.44
    HtmlAttribute
    -0.44
    going
    -0.41
     experiencing
    -0.41
     geworden
    -0.41
    ILED
    -0.40
     behold
    -0.40
    AHN
    -0.40
    hé
    -0.38
    POSITIVE LOGITS
     BorderRadius
    0.79
    HomeAsUpEnabled
    0.74
    RectangleBorder
    0.68
    adə
    0.68
     lend
    0.67
    zzleHttp
    0.67
     MonoBehaviour
    0.67
    bình
    0.66
     Reveal
    0.64
    发表于
    0.64
    Activations Density 0.003%

    No Known Activations