© 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. 0-CLT-HP
    7. 43433
    Prev
    Next
    INDEX
    Explanations

    reasons and components

    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
     primarily
    -1.30
     principally
    -1.22
    primarily
    -1.22
     Mainly
    -1.20
     mainly
    -1.20
     Primarily
    -1.18
     chiefly
    -1.17
    mainly
    -1.13
    Mainly
    -1.06
    DebuggerNonUser
    -1.01
    POSITIVE LOGITS
     be
    0.52
     N
    0.47
     recognized
    0.44
     I
    0.44
     
    0.43
    s
    0.42
     discovered
    0.41
     realized
    0.41
    trico
    0.41
     si
    0.41
    Activations Density 0.053%

    No Known Activations