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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5470
    Prev
    Next
    INDEX
    Explanations

    hardly

    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
     <>",
    -0.52
     atât
    -0.50
    ogaster
    -0.49
     Wiktionnaire
    -0.48
    sime
    -0.46
    gridx
    -0.45
    isuus
    -0.45
     jScrollPane
    -0.45
    ellón
    -0.44
     any
    -0.43
    POSITIVE LOGITS
     gynnwys
    0.62
    GraphicsUnit
    0.61
    requireNonNull
    0.55
     Besoin
    0.53
    olta
    0.52
     Suff
    0.51
    得上
    0.51
     lccn
    0.51
    công
    0.50
    qai
    0.50
    Activations Density 0.005%

    No Known Activations