© 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. 42344
    Prev
    Next
    INDEX
    Explanations

    heartfelt

    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
    StoryboardSegue
    -1.02
    AndEndTag
    -0.82
     nahilalakip
    -0.81
     MainAxisSize
    -0.80
     refroid
    -0.80
    CppMethod
    -0.77
    SharedDtor
    -0.77
    ed
    -0.75
    nodoc
    -0.74
    RTEE
    -0.74
    POSITIVE LOGITS
     inclined
    0.40
     unre
    0.37
     ini
    0.36
    schlag
    0.35
    "$
    0.35
     un
    0.34
     percent
    0.34
     sust
    0.34
     "
    0.34
     tra
    0.34
    Activations Density 0.052%

    No Known Activations