© 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. 5874
    Prev
    Next
    INDEX
    Explanations

    instructions or steps

    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
    ABUL
    -0.52
    complexType
    -0.51
    ℚ
    -0.49
     pulumi
    -0.48
    ysaccharides
    -0.48
     дописавши
    -0.46
    OrCreate
    -0.46
    nehmer
    -0.45
     SSSR
    -0.45
    нитель
    -0.44
    POSITIVE LOGITS
    Билгалдахарш
    0.67
    "]
    0.59
    httphttps
    0.58
    )}</
    0.57
    "])
    0.57
     estekak
    0.53
    "],
    0.53
    XmlAccessorType
    0.52
    "]))
    0.52
    DebuggerNonUser
    0.51
    Activations Density 0.000%

    No Known Activations