© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 396
    Prev
    Next
    INDEX
    Explanations

    medical reconstruction

    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
     Reconstruction
    -0.84
     TestBed
    -0.63
     reconstruction
    -0.60
    Reconstruction
    -0.60
    ParallelGroup
    -0.59
    tone
    -0.54
    d
    -0.45
    tones
    -0.44
     Caterina
    -0.42
    TestBed
    -0.42
    POSITIVE LOGITS
    SequentialGroup
    0.65
     DataTypes
    0.60
    InputBorder
    0.59
     оригіналу
    0.59
     محفوظة
    0.58
    ⓧ
    0.57
    getWriter
    0.56
     Designs
    0.56
    izações
    0.56
    chism
    0.55
    Activations Density 0.006%

    No Known Activations