© 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. 92547
    Prev
    Next
    INDEX
    Explanations

    Also

    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
     propOrder
    -1.20
    StoryboardSegue
    -1.16
    ]")]
    -0.99
    Personendaten
    -0.92
    GEBURTSDATUM
    -0.86
     ProtoMessage
    -0.84
    webElementXpaths
    -0.83
     bezeichneter
    -0.83
     EconPapers
    -0.82
    Espèce
    -0.81
    POSITIVE LOGITS
     Let
    0.81
    .
    0.79
     Then
    0.73
     Not
    0.72
     No
    0.66
     Don
    0.66
     However
    0.66
     Tell
    0.65
     Do
    0.64
     Yet
    0.64
    Activations Density 0.015%

    No Known Activations