© 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. 90911
    Prev
    Next
    INDEX
    Explanations

    0

    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
    findpost
    -0.71
    PyExc
    -0.68
     ***!
    -0.65
    DockStyle
    -0.64
    TypedDataSet
    -0.63
     &___
    -0.63
    PerformLayout
    -0.60
    TabIndex
    -0.60
    MENAFN
    -0.60
     AssemblyTitle
    -0.59
    POSITIVE LOGITS
     
    0.64
    REDIT
    0.48
    UTS
    0.46
    UER
    0.44
     ģ
    0.44
    BY
    0.44
     nocturne
    0.44
     milyen
    0.43
    UDO
    0.43
     scena
    0.43
    Activations Density 0.000%

    No Known Activations