© 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. 5990
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    FTFY
    -0.74
     OFDb
    -0.73
    findpost
    -0.73
     doInBackground
    -0.71
    '])){
    -0.70
     <<<<<<<<<<<<<<
    -0.69
     kasarigan
    -0.66
    }))
    -0.66
    .",
    -0.66
    enumii
    -0.64
    POSITIVE LOGITS
    rab
    0.41
    uvo
    0.41
    hele
    0.40
    existsSync
    0.39
    OnDelete
    0.39
     aéri
    0.39
    uib
    0.39
     psicológico
    0.36
     rayons
    0.36
     soutenu
    0.36
    Activations Density 0.004%

    No Known Activations