© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93165
    Prev
    Next
    INDEX
    Explanations

    positive outcomes

    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
     }}$}
    -0.76
     cdti
    -0.76
     photolibrary
    -0.68
    )•
    -0.68
    〗
    -0.68
    ">:
    -0.68
     calldata
    -0.67
    []
    -0.65
    AGGIO
    -0.65
     BRARY
    -0.63
    POSITIVE LOGITS
    .
    0.74
     to
    0.63
     on
    0.59
    ⓧ
    0.54
    ,
    0.52
    !
    0.50
    fjspx
    0.48
    ftagPool
    0.48
    nott
    0.48
    oredCriteria
    0.47
    Activations Density 0.043%

    No Known Activations