© 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. 5504
    Prev
    Next
    INDEX
    Explanations

    marketing and advertising

    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
     angeb
    -0.55
    ="#"><
    -0.52
     térm
    -0.51
    InitVars
    -0.47
     mêmes
    -0.47
    Featured
    -0.46
    ="#">
    -0.46
    willReturn
    -0.43
     Werbung
    -0.42
     Featured
    -0.42
    POSITIVE LOGITS
    endphp
    0.59
    UVWXYZ
    0.59
    diğim
    0.58
    Datuak
    0.58
    KURZBESCHREIBUNG
    0.56
    InjectAttribute
    0.54
     handcuffs
    0.53
    Coordenadas
    0.53
    GOTREF
    0.53
    PYX
    0.52
    Activations Density 0.004%

    No Known Activations