© 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. 91471
    Prev
    Next
    INDEX
    Explanations

    digital

    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
    limus
    -0.59
    PasswordEncoder
    -0.57
     rând
    -0.56
    */),
    -0.55
    }")]
    -0.52
     Reason
    -0.51
     particuliers
    -0.49
     piena
    -0.49
    SequentialGroup
    -0.49
     Thrones
    -0.48
    POSITIVE LOGITS
     veh
    0.63
     jScrollPane
    0.59
     vehicle
    0.59
     vehicles
    0.57
    hemat
    0.56
    saraba
    0.56
     VEH
    0.53
    بوابة
    0.52
     Vehicle
    0.52
    vehicle
    0.52
    Activations Density 0.004%

    No Known Activations