© 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. 1-CLT-HP
    7. 9801
    Prev
    Next
    INDEX
    Explanations

    Locations and names

    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
    FormTagHelper
    -0.62
     مشين
    -0.60
    issauga
    -0.56
    esthe
    -0.52
    entyfik
    -0.51
    RLock
    -0.51
    ANTAGE
    -0.51
    aways
    -0.50
    naker
    -0.50
    OGN
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.68
     ModelRenderer
    0.64
    AsUp
    0.58
    DebuggerNonUser
    0.57
    Portale
    0.54
     GenerationType
    0.53
    getDoctrine
    0.53
    ="@+
    0.51
     MutableLiveData
    0.51
    WireFormatLite
    0.50
    Activations Density 0.021%

    No Known Activations