© 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. 92499
    Prev
    Next
    INDEX
    Explanations

    questions, articles

    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
    ValueStyle
    -0.53
    OGND
    -0.48
    Persona
    -0.47
     bēr
    -0.43
    contentLoaded
    -0.43
     Aufl
    -0.43
     BIBSYS
    -0.42
    rifuge
    -0.42
     Benfica
    -0.41
     nepiecieš
    -0.41
    POSITIVE LOGITS
     становника
    0.65
    =?";
    0.60
    новништво
    0.60
    Personendaten
    0.58
     NSCoder
    0.57
     Registers
    0.57
    uxxxx
    0.57
     CascadeType
    0.57
     BoxFit
    0.56
     ModelExpression
    0.56
    Activations Density 0.006%

    No Known Activations