© 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. 91248
    Prev
    Next
    INDEX
    Explanations

    to

    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
    cinogenicity
    -0.81
     IBOutlet
    -0.72
    stdafx
    -0.68
     metav
    -0.67
     NAA
    -0.66
    clerview
    -0.66
    Xna
    -0.65
    clusal
    -0.65
    ]")]
    -0.65
     Americans
    -0.65
    POSITIVE LOGITS
     given
    0.47
    Given
    0.45
    ▾
    0.42
     Given
    0.38
    given
    0.36
     yourself
    0.36
    Chham
    0.35
     ing
    0.35
     ainsi
    0.35
    лтемелер
    0.35
    Activations Density 0.002%

    No Known Activations