© 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. 1-CLT-HP
    7. 16105
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/Terminology

    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
    Negative Logits
    ագրություններ
    -0.76
    UnusedPrivate
    -0.66
     @"/
    -0.65
    SequentialGroup
    -0.63
    esModule
    -0.63
    Personendaten
    -0.61
     Administrativna
    -0.60
    LElement
    -0.60
    AndroidJUnit
    -0.58
     imageNamed
    -0.58
    POSITIVE LOGITS
    KEYCODE
    0.53
    защи
    0.48
    ese
    0.46
    pagestyle
    0.45
    ase
    0.45
    чем
    0.43
     screening
    0.42
     screens
    0.42
     consi
    0.42
    xymatrix
    0.42
    Activations Density 0.016%

    No Known Activations