© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95414
    Prev
    Next
    INDEX
    Explanations

    medical, biological texts

    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
     متعلقه
    -0.69
     blink
    -0.63
    TargetException
    -0.60
    intéress
    -0.59
    WillAppear
    -0.59
    semb
    -0.55
     ActionListener
    -0.52
     Hierarchy
    -0.52
    Hier
    -0.51
    disposing
    -0.51
    POSITIVE LOGITS
    i
    0.84
    e
    0.77
    a
    0.65
    ה
    0.65
    o
    0.65
    }*/
    0.59
    inette
    0.58
    otho
    0.58
    ForValue
    0.57
     vPvB
    0.57
    Activations Density 0.051%

    No Known Activations