© 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. 5-CLT-HP
    7. 4134
    Prev
    Next
    INDEX
    Explanations

    muscles/body building

    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
     ActivatedRoute
    -0.58
    ιού
    -0.55
    RegistryLite
    -0.54
    COLOG
    -0.52
    ftagPool
    -0.52
    WebServlet
    -0.51
     betweenstory
    -0.51
    NOST
    -0.51
     ohms
    -0.50
    kraut
    -0.50
    POSITIVE LOGITS
    stdc
    0.63
     JpaRepository
    0.51
     فريبيس
    0.51
     externi
    0.49
     voren
    0.49
    Lähteet
    0.47
    ScopeManager
    0.47
    ]-->
    0.45
    anmoins
    0.45
     body
    0.45
    Activations Density 0.014%

    No Known Activations