© 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. 42957
    Prev
    Next
    INDEX
    Explanations

    code

    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
     OnClickListener
    -0.55
     Himo
    -0.54
     nerf
    -0.51
    uxxxx
    -0.51
     Kardinal
    -0.51
    OnClickListener
    -0.49
     AttributeSet
    -0.49
    Aiheesta
    -0.48
     PopupWindow
    -0.48
     ис
    -0.47
    POSITIVE LOGITS
     ddelweddau
    0.71
     متعلقه
    0.67
    protoimpl
    0.64
    tagHelperRunner
    0.63
     autorytatywna
    0.63
     gynhyrchwyd
    0.62
    StructEnd
    0.62
    Tikang
    0.59
    ✨:
    0.57
    Enllaces
    0.56
    Activations Density 1.538%

    No Known Activations