© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41135
    Prev
    Next
    INDEX
    Explanations

    presence/absence

    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
     presence
    -1.31
    presence
    -0.98
     absence
    -0.91
     Presence
    -0.90
    protoimpl
    -0.89
     présence
    -0.86
     otomatig
    -0.82
     presencia
    -0.78
    MigrationBuilder
    -0.77
    Presence
    -0.75
    POSITIVE LOGITS
    e
    0.53
     rechange
    0.46
    omány
    0.46
     détaillé
    0.46
     strtotime
    0.46
     altrett
    0.44
    Confusion
    0.44
     quieras
    0.43
     Illusion
    0.42
     scatola
    0.42
    Activations Density 0.066%

    No Known Activations