© 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. 91420
    Prev
    Next
    INDEX
    Explanations

    decides

    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
    __(/*!
    -0.76
    BeginContext
    -0.63
    Джерела
    -0.60
     MainAxisSize
    -0.59
    脚注の使い方
    -0.58
    enterOuterAlt
    -0.57
    Einzelnachweise
    -0.57
    Personendaten
    -0.56
     consultato
    -0.55
    Literatur
    -0.52
    POSITIVE LOGITS
    endphp
    0.56
     chaînes
    0.47
     arrangements
    0.46
     successivo
    0.44
    ONCE
    0.43
    Once
    0.42
    AsUp
    0.42
     setUsername
    0.42
     հղումներ
    0.41
     once
    0.41
    Activations Density 0.000%

    No Known Activations