© 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. 10228
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
     للمعارف
    -0.84
    ReusableCell
    -0.82
    GEBURTS
    -0.82
    caten
    -0.81
    rungsseite
    -0.77
    原始内容存档于
    -0.76
     дописавши
    -0.75
     ujednoznacz
    -0.73
    batore
    -0.72
    Hentet
    -0.71
    POSITIVE LOGITS
     ++)
    0.58
     doInBackground
    0.48
    形
    0.47
    故
    0.47
    anki
    0.45
    得
    0.42
    性
    0.41
    IsRequired
    0.41
    }{|
    0.40
    ||}
    0.40
    Activations Density 0.101%

    No Known Activations