© 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. 1-CLT-HP
    7. 9099
    Prev
    Next
    INDEX
    Explanations

    matured

    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
    CodedInputStream
    -0.46
    BRIGHT
    -0.44
     defenses
    -0.44
    ennia
    -0.44
    [:]
    -0.43
     darauf
    -0.42
     Uns
    -0.42
     Affiliations
    -0.42
    Uns
    -0.42
     gång
    -0.40
    POSITIVE LOGITS
    andExpect
    0.66
     виправивши
    0.65
    volving
    0.61
    ed
    0.60
     exchanging
    0.60
    ChildScrollView
    0.59
    volves
    0.59
    esModule
    0.59
    theless
    0.59
    хь
    0.59
    Activations Density 0.008%

    No Known Activations