© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3151
    Prev
    Next
    INDEX
    Explanations

    able suffix

    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
     vectorielles
    -0.69
     berätt
    -0.67
     récents
    -0.67
     récentes
    -0.67
     juridiques
    -0.67
    horabuena
    -0.67
     âmes
    -0.66
     débats
    -0.65
     chère
    -0.65
     autorytatywna
    -0.64
    POSITIVE LOGITS
     material
    0.56
     bodies
    0.56
     body
    0.55
     terrain
    0.55
     streets
    0.54
     substances
    0.53
     volumes
    0.51
     acquisitions
    0.51
     condition
    0.49
     materials
    0.49
    Activations Density 0.001%

    No Known Activations