© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1118
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
     Италијани
    -0.66
    omiast
    -0.63
     Roskov
    -0.63
    Viki
    -0.61
    UnsafeEnabled
    -0.59
     OnInit
    -0.57
     "..\..\..\
    -0.55
    Anyways
    -0.55
     También
    -0.54
     Also
    -0.52
    POSITIVE LOGITS
     was
    0.74
     not
    0.74
     wasn
    0.69
     yes
    0.69
     is
    0.67
    not
    0.65
     isn
    0.63
     could
    0.60
     hadn
    0.59
    HasIndex
    0.58
    Activations Density 0.001%

    No Known Activations