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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45550
    Prev
    Next
    INDEX
    Explanations

    will

    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
    igshid
    -0.68
    UnusedPrivate
    -0.63
     sait
    -0.59
    y
    -0.59
     will
    -0.54
    liest
    -0.54
    THISDAY
    -0.54
     expects
    -0.53
    lably
    -0.53
     the
    -0.53
    POSITIVE LOGITS
     kasarigan
    0.80
    HasAnnotation
    0.66
    StructEnd
    0.61
     suffice
    0.60
     ensue
    0.57
     betweenstory
    0.56
     enable
    0.56
    хьтан
    0.52
     drown
    0.51
     pave
    0.50
    Activations Density 0.117%

    No Known Activations