© 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. 92221
    Prev
    Next
    INDEX
    Explanations

    code/definitions

    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
    HostException
    -0.65
    AccessException
    -0.63
    protoimpl
    -0.61
     Dage
    -0.59
    AnchorStyles
    -0.56
     onCreateView
    -0.55
    })->
    -0.54
    ruptedException
    -0.53
    MLLoader
    -0.53
     pattes
    -0.52
    POSITIVE LOGITS
     nahilalakip
    0.56
     propuesto
    0.52
    :✨
    0.50
     PLWABN
    0.48
    kadang
    0.46
     gyhoeddwyd
    0.46
    zzlement
    0.46
     afhankelijk
    0.44
     used
    0.43
     sued
    0.43
    Activations Density 0.003%

    No Known Activations