© 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. 5-CLT-HP
    7. 6032
    Prev
    Next
    INDEX
    Explanations

    changes/shifts

    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
    <bos>
    -0.49
    Sure
    -0.43
    rungsseite
    -0.42
    Aholisi
    -0.42
     protons
    -0.42
     ?>">
    -0.41
     sure
    -0.39
    декс
    -0.39
     certainly
    -0.39
     douze
    -0.39
    POSITIVE LOGITS
     beast
    0.81
     different
    0.75
     animal
    0.73
    ineno
    0.71
     separate
    0.71
    LElement
    0.71
    PreferredItem
    0.71
    MLLoader
    0.70
    וויק
    0.68
     seperate
    0.68
    Activations Density 0.001%

    No Known Activations