© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    valves

    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
     valves
    -0.69
     valve
    -0.64
    tration
    -0.64
     يتيمه
    -0.63
    valve
    -0.59
     válvulas
    -0.56
    íž
    -0.54
    FailureListener
    -0.53
     Chwiliwch
    -0.51
    sama
    -0.50
    POSITIVE LOGITS
    PreInfinity
    0.61
    EDEFAULT
    0.57
     blobs
    0.57
    ChildScrollView
    0.55
    IntoConstraints
    0.54
    ViewFeatures
    0.54
    ilent
    0.52
    niken
    0.52
    filo
    0.51
    @[+][
    0.50
    Activations Density 0.017%

    No Known Activations